{"meta":{"query_hash":"e5a6f3e02b51","filters":{"venue":"Big Data & Society"},"cohort_total":74,"direct_labels_cover":1,"predictions_cover":74,"exported":74,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/e5a6f3e02b51","api":"https://metacan.xera.ac/api/v1/cohort?venue=Big+Data+%26+Society"},"results":[{"id":"W2111205063","doi":"10.1177/2053951714564228","title":"How web tracking changes user agency in the age of Big Data: The used user","year":2014,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Big data; The Internet; Tracking (education); Agency (philosophy); Computer science; Internet privacy; Task (project management); Social media; World Wide Web; Personally identifiable information; Scale (ratio); Politics; Data science; Computer security; Engineering; Sociology; Political science; Law","score_opus":0.2408572523367829,"score_gpt":0.34116140219044927,"score_spread":0.10030414985366637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111205063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72831076,0.005936632,0.025820242,0.20327942,0.010390485,0.0059287986,0.013051058,0.00053689873,0.0067457315],"genre_scores_gemma":[0.99169743,0.0026399808,0.00037123304,0.001157558,0.0025069176,0.00002505288,0.0013761371,0.000016338883,0.00020932184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975109,0.00074693415,0.00019654563,0.00050067366,0.00065794087,0.00038698612],"domain_scores_gemma":[0.9962436,0.00040690132,0.0001737298,0.0030819443,0.000049657287,0.00004414919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005791523,0.00014850007,0.00019512021,0.000025132089,0.00069247757,0.00041829605,0.005221055,0.00016535462,0.000016762204],"category_scores_gemma":[0.0015606831,0.00009367923,0.00006755174,0.0005725019,0.0004640986,0.001022148,0.0017313361,0.0003483582,0.00000885087],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025371683,0.00048597238,0.01493644,0.00019782194,0.00014983439,0.000008527216,0.1821862,9.138331e-7,0.00584456,0.0061814673,0.58174074,0.20824218],"study_design_scores_gemma":[0.00029613735,0.000019160709,0.011070266,0.000026958369,0.000038550308,9.958696e-7,0.01360988,0.0001791076,0.000061471335,0.0007189023,0.9738257,0.00015286785],"about_ca_topic_score_codex":0.0059224744,"about_ca_topic_score_gemma":0.0739698,"teacher_disagreement_score":0.392085,"about_ca_system_score_codex":0.000039157312,"about_ca_system_score_gemma":0.00013989683,"threshold_uncertainty_score":0.9702106},"labels":[],"label_agreement":null},{"id":"W2127418522","doi":"10.1177/2053951715589417","title":"Networks of digital humanities scholars: The informational and social uses and gratifications of Twitter","year":2015,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Uses and gratifications theory; Social media; Sociology; Big data; Digital humanities; Attendance; Thematic analysis; Social network (sociolinguistics); Media studies; Value (mathematics); Public relations; World Wide Web; Social science; Qualitative research; Political science; Computer science","score_opus":0.35164700424740775,"score_gpt":0.35676669479565276,"score_spread":0.005119690548245015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127418522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9730142,0.00050411373,0.0019004415,0.004785964,0.0002349162,0.00035194049,0.0010438665,0.000039857674,0.018124707],"genre_scores_gemma":[0.9987879,0.00014959842,0.00011407481,0.00042329455,0.00013350889,7.854584e-7,0.00024272822,0.0000019775416,0.0001461757],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99939716,0.000027273276,0.00018313646,0.000049575538,0.00025668382,0.00008618498],"domain_scores_gemma":[0.99946946,0.00008069972,0.0001361742,0.00013701012,0.00014165368,0.000035012265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006111956,0.000043881577,0.000069662616,0.000011638846,0.0003456187,0.0002369518,0.00020537127,0.00004704718,0.000009693099],"category_scores_gemma":[0.00017773492,0.00003187915,0.000019973797,0.00009212533,0.00062742474,0.0017418794,0.00013138959,0.000065006905,0.0000013842426],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007663032,0.00003608616,0.0035047971,0.000034044468,0.0000586677,2.0484022e-8,0.7024112,0.000008083183,0.000008824376,0.039151836,0.23885024,0.015928568],"study_design_scores_gemma":[0.00053952227,0.000024722898,0.047718436,0.000020044525,0.000034889974,0.0000013878512,0.55019027,0.0014865794,0.000011257308,0.001382149,0.39843073,0.0001600259],"about_ca_topic_score_codex":0.0001006738,"about_ca_topic_score_gemma":0.00008507423,"teacher_disagreement_score":0.1595805,"about_ca_system_score_codex":0.000011708533,"about_ca_system_score_gemma":0.00015079454,"threshold_uncertainty_score":0.26582545},"labels":[],"label_agreement":null},{"id":"W2138016069","doi":"10.1177/2053951714541861","title":"Surveillance, Snowden, and Big Data: Capacities, consequences, critique","year":2014,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":825,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Big data; Metadata; Sociology; Transparency (behavior); Panopticon; The Internet; Internet privacy; Data science; Political science; Computer security; Computer science; Law; Politics; World Wide Web","score_opus":0.11960032265849,"score_gpt":0.31827137554777013,"score_spread":0.19867105288928014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138016069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4736162,0.029894294,0.022496723,0.022604898,0.008887025,0.003819375,0.41613397,0.0027062641,0.019841233],"genre_scores_gemma":[0.91528636,0.0064965333,0.0045677405,0.0062660635,0.0027333647,0.000024368657,0.06382701,0.000077251054,0.00072130724],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99706656,0.00023681164,0.0004391488,0.0012120453,0.0005074677,0.0005379958],"domain_scores_gemma":[0.99423623,0.00038387103,0.00015037044,0.004657909,0.0001741736,0.0003974632],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017400462,0.0003228618,0.0006172615,0.000035167814,0.00020394477,0.00011689455,0.0011741698,0.00018070062,0.000060524846],"category_scores_gemma":[0.0012307981,0.0002946821,0.00007747648,0.0002762832,0.0013810797,0.0004435492,0.0015188216,0.0003642167,0.000056517252],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057790614,0.00011678084,0.045084894,0.0005010053,0.00022985452,0.00004098087,0.0002639195,2.0580045e-7,0.00096265407,0.0003314924,0.90821755,0.044192854],"study_design_scores_gemma":[0.0016656074,0.00007179078,0.05163749,0.00014735643,0.000093740055,0.00013814759,0.00063181936,0.0009612994,0.000067818386,0.00019415158,0.9439583,0.00043252046],"about_ca_topic_score_codex":0.001072314,"about_ca_topic_score_gemma":0.0013185282,"teacher_disagreement_score":0.44167015,"about_ca_system_score_codex":0.0000641977,"about_ca_system_score_gemma":0.0004930328,"threshold_uncertainty_score":0.9999505},"labels":[],"label_agreement":null},{"id":"W2144304780","doi":"10.1177/2053951714535365","title":"Big Data, social physics, and spatial analysis: The early years","year":2014,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Geographer; Epistemology; Big data; Natural (archaeology); Sociology; Social science; History; Geography; Computer science; Economic geography","score_opus":0.15681002574232464,"score_gpt":0.2544487952600075,"score_spread":0.09763876951768288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144304780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38994446,0.0045842202,0.5114833,0.004925939,0.0025178182,0.0005571044,0.082807586,0.00018903581,0.0029904929],"genre_scores_gemma":[0.98751503,0.00042603086,0.0002894538,0.0006199015,0.0028335399,0.0000047373524,0.008157009,0.000018054865,0.00013621757],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984339,0.00004037319,0.00038787327,0.00077980594,0.000088108194,0.00026993666],"domain_scores_gemma":[0.9974693,0.00008439777,0.0002827527,0.0020772773,0.000020975293,0.00006528985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010825312,0.00015795395,0.00043975076,0.000043331554,0.00030679873,0.0002631797,0.0015216799,0.00010453215,0.0000666751],"category_scores_gemma":[0.0000812136,0.00014273029,0.00018940392,0.0006237115,0.0001764314,0.0003297129,0.0012211356,0.00018709173,0.00021365473],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020835592,0.00018541058,0.28040436,0.000041244628,0.006018593,0.0000018552148,0.0043090964,0.0000245343,0.00001895549,0.007577307,0.1318091,0.5695887],"study_design_scores_gemma":[0.00047653043,0.000022214164,0.60353607,0.0000030605045,0.0008695168,4.1414413e-7,0.00021820373,0.06530281,0.0000024497417,0.0029961588,0.32618222,0.00039037538],"about_ca_topic_score_codex":0.021541042,"about_ca_topic_score_gemma":0.0035932066,"teacher_disagreement_score":0.5975706,"about_ca_system_score_codex":0.000016485525,"about_ca_system_score_gemma":0.000018495686,"threshold_uncertainty_score":0.9849746},"labels":[],"label_agreement":null},{"id":"W2278861975","doi":"10.1177/2053951715621570","title":"Introduction to Articles from the 2014 Conference on Social Media &amp; Society","year":2015,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Smart Cities and Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"University of Toronto","keywords":"Social media; Big data; Key (lock); Computer science; Data science; World Wide Web; User-generated content; Internet privacy; Sociology; Media studies; Computer security; Data mining","score_opus":0.1802755278518888,"score_gpt":0.26978518292843434,"score_spread":0.08950965507654554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278861975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9213401,0.00088631804,0.01440266,0.05344439,0.005016839,0.00033516233,0.0021061895,0.0019524507,0.0005158618],"genre_scores_gemma":[0.9799176,0.00079341634,0.007717363,0.0010084038,0.009266576,0.000029981707,0.0011505226,0.000041619456,0.00007454725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991272,0.00001592751,0.00013048963,0.00026433702,0.00023241685,0.00022963388],"domain_scores_gemma":[0.9989956,0.00010847,0.00002220739,0.0007710848,0.00004827286,0.00005436675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002776979,0.00013019748,0.00012735405,0.000005628446,0.00013106328,0.00009197926,0.0006007218,0.00012526872,0.000051986826],"category_scores_gemma":[0.00014772125,0.00009800425,0.00007199387,0.00013987818,0.00011892575,0.00012882655,0.00033466995,0.000228093,0.00036351098],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032937564,0.000009303311,0.00009267261,0.0000033190254,0.000048596317,9.2340855e-8,0.005192588,0.000050082075,0.00074649963,0.00041584743,0.97387546,0.019562233],"study_design_scores_gemma":[0.00027365284,0.000011728382,0.0037410401,0.000008561951,0.000029492234,6.6796105e-7,0.013481151,0.0025281487,0.0008322296,0.0019606284,0.97690594,0.00022674036],"about_ca_topic_score_codex":0.00011006121,"about_ca_topic_score_gemma":0.00034769528,"teacher_disagreement_score":0.05857744,"about_ca_system_score_codex":0.00007502207,"about_ca_system_score_gemma":0.000028440641,"threshold_uncertainty_score":0.46723196},"labels":[],"label_agreement":null},{"id":"W2345298843","doi":"10.1177/2053951716645828","title":"Social media and the social sciences: How researchers employ Big Data analytics","year":2016,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Social Media and Politics","field":"Social Sciences","cited_by":175,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Social media; Social media analytics; Big data; Data science; Analytics; Computer science; Internet privacy; Data analysis; World Wide Web; Sociology; Data mining","score_opus":0.6222554240675415,"score_gpt":0.4621015055218677,"score_spread":0.16015391854567385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345298843","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18155628,0.0024863111,0.0013216212,0.7830788,0.007884766,0.0016141841,0.010820602,0.000504088,0.010733341],"genre_scores_gemma":[0.97387445,0.0039957324,0.00035881283,0.0017627038,0.018925315,0.000015988793,0.00027655257,0.000033457658,0.00075701583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954781,0.0009135035,0.0002560379,0.0007372858,0.0015950552,0.0010200442],"domain_scores_gemma":[0.9946848,0.0037916182,0.00017522626,0.0009393397,0.00017379837,0.00023521525],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0060523595,0.0002011688,0.0003420737,0.000036919766,0.0043617124,0.0005685418,0.0039334763,0.00032175574,0.000031327538],"category_scores_gemma":[0.006997539,0.00012328854,0.00012860815,0.0008838393,0.012968775,0.0006949818,0.002181993,0.00034140734,0.000025276433],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023403469,0.00004183988,0.0033776015,0.000016948492,0.00013397618,0.0000024509097,0.13009804,6.776482e-9,0.000047882837,0.023545211,0.75067073,0.092041925],"study_design_scores_gemma":[0.0018702735,0.000017224434,0.0026005267,0.00002718833,0.00016814512,7.801661e-7,0.16793637,0.0000596396,0.000011909397,0.0113464715,0.8155729,0.00038856492],"about_ca_topic_score_codex":0.0020740507,"about_ca_topic_score_gemma":0.004470967,"teacher_disagreement_score":0.79231817,"about_ca_system_score_codex":0.00016335992,"about_ca_system_score_gemma":0.0016012551,"threshold_uncertainty_score":0.9969345},"labels":[],"label_agreement":null},{"id":"W2475266777","doi":"10.1177/2053951716648174","title":"Big Data in food and agriculture","year":2016,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Agriculture, Land Use, Rural Development","field":"Agricultural and Biological Sciences","cited_by":418,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; St. Thomas University","funders":"","keywords":"Big data; Scholarship; Agriculture; Data science; Affordance; Computer science; Economics; Economic growth; Data mining","score_opus":0.11386336935906238,"score_gpt":0.23990073082089722,"score_spread":0.12603736146183483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475266777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904938,0.0011667226,0.000014384508,0.003864276,0.00036334695,0.00026911456,0.0035614378,0.000083762614,0.00018316653],"genre_scores_gemma":[0.9900789,0.0026087565,0.00037929422,0.000663093,0.0012694523,0.0000123328155,0.004420417,0.0000015963807,0.00056614395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99823314,0.00005078554,0.00024595257,0.0007990229,0.0002854086,0.00038569552],"domain_scores_gemma":[0.9992086,0.0001412383,0.00008544357,0.00039029674,0.000038700528,0.00013572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003744623,0.00021584248,0.00021017695,0.000003706255,0.00016632452,0.00008734554,0.0013981711,0.00018739229,0.00003604711],"category_scores_gemma":[0.000077295306,0.000051470954,0.000042030082,0.0003661614,0.0000716479,0.00040849092,0.0020069617,0.00013220524,0.000037965543],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000113308615,0.000118555305,0.021495832,0.000015275577,0.000057293997,0.000004560499,0.00021236244,3.3492817e-8,0.021475388,0.00019412518,0.3806371,0.5757781],"study_design_scores_gemma":[0.00033210646,0.000059692782,0.55742806,0.000060971262,0.00001153334,0.00001129341,0.0005321628,0.00000416104,0.00043100724,0.00067852635,0.44013622,0.00031423432],"about_ca_topic_score_codex":0.00021057144,"about_ca_topic_score_gemma":0.0051074657,"teacher_disagreement_score":0.5754639,"about_ca_system_score_codex":0.000037895803,"about_ca_system_score_gemma":0.000016168704,"threshold_uncertainty_score":0.28500858},"labels":[],"label_agreement":null},{"id":"W2537383304","doi":"10.1177/2053951716674238","title":"Critical data studies: An introduction","year":2016,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":432,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Arts and Humanities Research Council; University College London","keywords":"Big data; Multitude; Data science; Theme (computing); Sociology; Epistemology; Computer science; Data mining; World Wide Web","score_opus":0.7517157753114562,"score_gpt":0.5101888192272449,"score_spread":0.24152695608421126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537383304","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025921755,0.0026950683,0.32987678,0.5957236,0.0040468876,0.00060413324,0.039801035,0.0010985314,0.0002321703],"genre_scores_gemma":[0.86880994,0.0068836557,0.105454974,0.0026982871,0.008736468,0.00007671584,0.0059568537,0.000055314336,0.001327816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679893,0.00008504961,0.0004535983,0.0015822285,0.0007760777,0.0003041359],"domain_scores_gemma":[0.9850859,0.001321568,0.00011324344,0.013045994,0.00033036195,0.00010291154],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.003708911,0.00013401954,0.00021984552,0.000031256684,0.0003650005,0.00024188346,0.0077478797,0.00014337391,0.00014705531],"category_scores_gemma":[0.016626716,0.00007338097,0.00004282488,0.0006242695,0.00080803386,0.0025793205,0.007139632,0.00015472723,0.00050381],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017527555,0.00004503547,0.0000701897,0.0000016071516,0.000014501012,2.7680153e-7,0.00004882887,4.965606e-8,0.0008052422,0.0056434576,0.67260015,0.3207689],"study_design_scores_gemma":[0.00013851676,0.000025648213,0.00049305643,0.0000057515795,0.000020571555,0.0000060220405,0.004950306,0.0005544246,0.00014179395,0.020851031,0.97267467,0.00013822413],"about_ca_topic_score_codex":0.000022435543,"about_ca_topic_score_gemma":0.00007436008,"teacher_disagreement_score":0.8428882,"about_ca_system_score_codex":0.00004093213,"about_ca_system_score_gemma":0.0000697156,"threshold_uncertainty_score":0.9976207},"labels":[],"label_agreement":null},{"id":"W2552915843","doi":"10.1177/2053951716666869","title":"The Snowden Archive-in-a-Box: A year of travelling experiments in outreach and education","year":2016,"lang":"en","type":"article","venue":"Big Data & Society","topic":"QR Code Applications and Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"Economic and Social Research Council","keywords":"Outreach; World Wide Web; Computer science; Political science; Law","score_opus":0.06873341372261689,"score_gpt":0.3011796647549415,"score_spread":0.23244625103232464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552915843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7261909,0.00249624,0.2646636,0.00507217,0.00016852679,0.00045270633,0.0000637808,0.00009365853,0.0007983773],"genre_scores_gemma":[0.9700749,0.0011530073,0.028656913,0.000023122773,0.000014368449,0.000028227712,0.000005568661,0.0000024714639,0.000041455598],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9995097,0.00001299781,0.00011109645,0.0002036686,0.00006794302,0.00009461074],"domain_scores_gemma":[0.9991069,0.00008395313,0.000038285467,0.00074895774,0.000010480178,0.000011452044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020105107,0.00004241243,0.000053074014,0.000017979486,0.000040181305,0.000028183182,0.0008159289,0.00002676844,3.8053403e-7],"category_scores_gemma":[0.000018470191,0.000025411959,0.000012731035,0.00013870672,0.00007717195,0.00013821,0.00042175184,0.00004058892,0.000002350959],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014155803,0.00008903385,0.0077254684,0.000005660825,0.0000061130036,1.107783e-7,0.001836209,1.8932937e-7,0.0076408098,0.021325314,0.0021098023,0.95925987],"study_design_scores_gemma":[0.003910909,0.00018439315,0.5724928,0.0006560857,0.000021797567,0.000014009823,0.021434965,0.021751637,0.07457619,0.14687656,0.15693833,0.001142354],"about_ca_topic_score_codex":0.00009711528,"about_ca_topic_score_gemma":0.000053117765,"teacher_disagreement_score":0.95811754,"about_ca_system_score_codex":0.000016487136,"about_ca_system_score_gemma":0.00005528108,"threshold_uncertainty_score":0.15162125},"labels":[],"label_agreement":null},{"id":"W2775078427","doi":"10.1177/2053951717745678","title":"Challenges in administrative data linkage for research","year":2017,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":356,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Economic and Social Research Council; Wellcome Trust","keywords":"Linkage (software); Record linkage; Computer science; Data quality; Data science; Data collection; Confidentiality; Data mining; Sample (material); Population; Computer security; Engineering; Statistics; Sociology","score_opus":0.9805021151538041,"score_gpt":0.681924870153455,"score_spread":0.2985772450003491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775078427","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02054836,0.01685871,0.056675423,0.4947101,0.008716423,0.010453798,0.18591082,0.00032732333,0.20579906],"genre_scores_gemma":[0.9244187,0.019760638,0.031172777,0.0013382344,0.0023792582,0.00018348428,0.012218664,0.00004949484,0.008478783],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99560934,0.00036895066,0.00049364823,0.0015490326,0.0015135409,0.00046548835],"domain_scores_gemma":[0.98190695,0.0026410192,0.00023717608,0.014890411,0.00021302435,0.0001114057],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.043281335,0.0001217356,0.00026117873,0.000056613997,0.0008379799,0.001330097,0.017246831,0.0001122376,0.000042092364],"category_scores_gemma":[0.017427856,0.00009554727,0.00005861652,0.00017658819,0.00048061064,0.002232797,0.014980306,0.00029884785,0.00020948189],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001755518,0.00011708596,0.00012636418,0.000027941005,0.000024636245,0.0000044367735,0.0013596436,1.0215941e-7,0.000008770851,0.007451819,0.6041026,0.38675904],"study_design_scores_gemma":[0.00047704368,0.000053241467,0.013985453,0.000030463236,0.0000067875812,4.708933e-7,0.016254015,0.0015982552,0.000016281761,0.017350942,0.95009947,0.00012757762],"about_ca_topic_score_codex":0.00024212286,"about_ca_topic_score_gemma":0.007538258,"teacher_disagreement_score":0.9038703,"about_ca_system_score_codex":0.000034576737,"about_ca_system_score_gemma":0.00022248088,"threshold_uncertainty_score":0.9997066},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2895190106","doi":"10.1177/2053951718809145","title":"Democratic governance in an age of datafication: Lessons from mapping government discourses and practices","year":2018,"lang":"en","type":"article","venue":"Big Data & Society","topic":"E-Government and Public Services","field":"Social Sciences","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Accountability; Enthusiasm; Transparency (behavior); Democracy; Government (linguistics); Public relations; Corporate governance; Public administration; Big data; Optimism; Political science; Sociology; Good governance; Open government; Law; Economics; Politics; Psychology; Computer science; Management; Social psychology","score_opus":0.21011758157523336,"score_gpt":0.4032978062416929,"score_spread":0.19318022466645957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895190106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9722825,0.0010901066,0.00023530985,0.01684655,0.00037260284,0.00025933565,0.0020643591,0.00003062982,0.0068185776],"genre_scores_gemma":[0.99291766,0.002305495,0.0029390466,0.00039463467,0.00079530734,0.0000065903723,0.0004450178,0.000007482445,0.00018876743],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983105,0.00014824745,0.0002176046,0.00040594506,0.0007113147,0.00020639529],"domain_scores_gemma":[0.9984136,0.00027949194,0.0005086525,0.00069004676,0.0000318879,0.000076319426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001057274,0.00009729918,0.00015028664,0.000004258215,0.00027164054,0.00017585674,0.0009373392,0.0000754736,0.00009830047],"category_scores_gemma":[0.00027120544,0.000091967,0.000021606918,0.00022202652,0.0005235763,0.001910631,0.00043156018,0.00009230301,0.0000042408574],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055079225,0.000843407,0.6942913,0.0001487584,0.00021143923,0.000006448852,0.14619827,5.436395e-7,0.005451755,0.03166929,0.043568775,0.0775549],"study_design_scores_gemma":[0.00048753197,0.000046094505,0.52089363,0.0001312896,0.000055062963,2.3580114e-7,0.15906282,0.000755925,0.00013557693,0.001550057,0.31659928,0.00028252893],"about_ca_topic_score_codex":0.013430848,"about_ca_topic_score_gemma":0.08167144,"teacher_disagreement_score":0.2730305,"about_ca_system_score_codex":0.00009971246,"about_ca_system_score_gemma":0.00012949592,"threshold_uncertainty_score":0.9931388},"labels":[],"label_agreement":null},{"id":"W2898230640","doi":"10.1177/2053951718805214","title":"Children’s digital playgrounds as data assemblages: Problematics of privacy, personalization, and promotional culture","year":2018,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Child Development and Digital Technology","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Brock University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Personalization; Internet privacy; Analytics; Digital media; Social media; Computer science; TRACE (psycholinguistics); The Internet; World Wide Web; Advertising; Sociology; Business; Data science","score_opus":0.10367909132279698,"score_gpt":0.3340405123595719,"score_spread":0.2303614210367749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898230640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9427904,0.001018136,0.010358812,0.0066040554,0.0006051199,0.0017384604,0.0054271757,0.0005701662,0.030887686],"genre_scores_gemma":[0.9879153,0.00038951027,0.0031955785,0.0001592035,0.00057433406,0.0000038610137,0.006803812,0.000012464074,0.00094596844],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985926,0.000023638988,0.00024390279,0.00045455043,0.00046501064,0.00022027308],"domain_scores_gemma":[0.9988087,0.000046185633,0.00015180338,0.0007645866,0.00015499216,0.00007373161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047174946,0.00012268398,0.00015925849,0.000021354834,0.00039681167,0.0002688267,0.0013506074,0.00017328284,0.000031568812],"category_scores_gemma":[0.0006208623,0.000107744214,0.00002964155,0.00032557276,0.00082920556,0.0013773697,0.0015645628,0.00009500355,0.000017723984],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015733553,0.00063959556,0.13715905,0.00017493904,0.00041591137,0.0000014881111,0.09047578,6.230979e-8,0.00015840959,0.053145815,0.69118947,0.02662375],"study_design_scores_gemma":[0.0022159708,0.00038184173,0.109562114,0.00038625966,0.00017333703,0.00006658267,0.030126741,0.00068078376,0.00021240182,0.047417957,0.8074084,0.0013676382],"about_ca_topic_score_codex":0.000087297674,"about_ca_topic_score_gemma":0.00017371654,"teacher_disagreement_score":0.11621892,"about_ca_system_score_codex":0.000037340207,"about_ca_system_score_gemma":0.00037070227,"threshold_uncertainty_score":0.43936813},"labels":[],"label_agreement":null},{"id":"W2936242438","doi":"10.1177/2053951719839433","title":"What are neural networks <i>not</i> good at? On artificial creativity","year":2019,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Creativity; Artificial neural network; Scope (computer science); Computer science; Artificial intelligence; Extrapolation; Sociology; Cognitive science; Psychology; Social psychology; Mathematics","score_opus":0.18321867859015584,"score_gpt":0.38280388535365095,"score_spread":0.19958520676349512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936242438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625265,0.0008090758,0.008066105,0.013047855,0.006172912,0.00061407464,0.00028836672,0.00025646877,0.008218647],"genre_scores_gemma":[0.9914235,0.00028060848,0.00063890975,0.0021889843,0.0018851624,0.0000050616936,0.00041126707,0.000012646175,0.0031538662],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796236,0.00040589165,0.00020061171,0.00051776686,0.0005827843,0.0003305913],"domain_scores_gemma":[0.9983205,0.0007306099,0.00016200232,0.0005959958,0.000074035306,0.00011682379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015429076,0.00013656552,0.00023516457,0.000014991972,0.0006229707,0.00031504684,0.0006072378,0.00012772932,0.00027097852],"category_scores_gemma":[0.000108967746,0.00012348883,0.00021903403,0.00041708176,0.00016066644,0.0006082303,0.00041172857,0.00020531756,0.00015457495],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013483776,0.0005513393,0.04801607,0.0000303049,0.0003743606,0.000008984433,0.010564295,0.0075039337,0.00023989535,0.009989875,0.14364286,0.77894324],"study_design_scores_gemma":[0.0006351192,0.000091256996,0.08083695,0.00008439204,0.00019432807,0.0000013770064,0.014040272,0.25757593,0.000093547555,0.0032779519,0.64230597,0.0008629219],"about_ca_topic_score_codex":0.00055320485,"about_ca_topic_score_gemma":0.0023409005,"teacher_disagreement_score":0.77808034,"about_ca_system_score_codex":0.00011030332,"about_ca_system_score_gemma":0.00007300115,"threshold_uncertainty_score":0.5035729},"labels":[],"label_agreement":null},{"id":"W2945267390","doi":"10.1177/2053951719843310","title":"Big Data and quality data for fake news and misinformation detection","year":2019,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":155,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Nvidia","keywords":"Misinformation; Computer science; Variety (cybernetics); Data science; Quality (philosophy); Fake news; Perspective (graphical); Big data; Appeal; Data quality; Internet privacy; Data mining; Artificial intelligence; Computer security","score_opus":0.35602260437338795,"score_gpt":0.4058609883183898,"score_spread":0.04983838394500184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945267390","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83571905,0.0015528192,0.092563614,0.0076692626,0.0045147575,0.003868583,0.039654773,0.00044401042,0.01401313],"genre_scores_gemma":[0.959827,0.0043191607,0.003365617,0.0028575044,0.0012842105,0.000003208938,0.02707639,0.000019239102,0.001247645],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862653,0.000072289215,0.00032773396,0.0003663011,0.00035402685,0.00025314232],"domain_scores_gemma":[0.9973335,0.000187331,0.00021463256,0.002049546,0.000068172565,0.00014681651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031700588,0.000108562,0.0001539325,0.000021715765,0.0005116636,0.00044566204,0.0010965869,0.00013683068,0.000023727584],"category_scores_gemma":[0.0008642844,0.00009937067,0.000019763937,0.00017452113,0.00013066245,0.0043026595,0.0011537237,0.00010053293,0.000027615186],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025437748,0.00002157943,0.00073283707,0.00016744764,0.00003757226,2.1832863e-8,0.023234418,3.1220006e-7,0.00020774535,0.00047583928,0.12713376,0.84796304],"study_design_scores_gemma":[0.0007538451,0.0000220333,0.006611254,0.000017246144,0.000027124377,9.12451e-7,0.0373719,0.010389292,0.000036796344,0.0000697597,0.94450814,0.00019172346],"about_ca_topic_score_codex":0.0023273493,"about_ca_topic_score_gemma":0.0056370883,"teacher_disagreement_score":0.8477713,"about_ca_system_score_codex":0.00003663929,"about_ca_system_score_gemma":0.00019203362,"threshold_uncertainty_score":0.42975292},"labels":[],"label_agreement":null},{"id":"W3005228004","doi":"10.1177/2053951720904112","title":"Manipulate to empower: Hyper-relevance and the contradictions of marketing in the age of surveillance capitalism","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Consumer Behavior in Brand Consumption and Identification","field":"Business, Management and Accounting","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Relevance (law); Contradiction; Marketing; Capitalism; Sociology; Empowerment; Digital marketing; Advertising; Business; Economics; Politics; Political science; Epistemology; Law","score_opus":0.10975634150883518,"score_gpt":0.2702810269982159,"score_spread":0.1605246854893807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005228004","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904707,0.00065815065,0.00017405742,0.00791198,0.00017120142,0.0003389764,0.00007144232,0.000017685164,0.00018582212],"genre_scores_gemma":[0.99771744,0.0003198191,0.00004837802,0.0016414926,0.00011197263,0.000012019486,0.0001241467,0.000005845355,0.000018900451],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99925613,0.000053556498,0.00025526434,0.00019066942,0.0001550626,0.00008928684],"domain_scores_gemma":[0.99920785,0.00020954416,0.00013175952,0.00039096555,0.00005376159,0.000006107238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013177275,0.00007044907,0.00013776352,0.000015768412,0.00009822451,0.00009013944,0.00042515816,0.000024764553,0.000016904078],"category_scores_gemma":[0.00030614002,0.000047625705,0.00004822329,0.00029036534,0.00013502616,0.0002137766,0.0001919665,0.00008343252,0.0000071937848],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009449512,0.00033978772,0.55359685,0.0012450638,0.00020507732,0.0000072051644,0.015181187,0.000031599797,0.02968578,0.0075914045,0.11710265,0.27406844],"study_design_scores_gemma":[0.00077247736,0.0000010329402,0.93107665,0.000026632926,0.000040292678,6.349935e-7,0.0015358225,0.0010651968,0.0000069042553,0.000041712115,0.06535629,0.000076356904],"about_ca_topic_score_codex":0.0005787747,"about_ca_topic_score_gemma":0.00034783644,"teacher_disagreement_score":0.3774798,"about_ca_system_score_codex":0.0000039555684,"about_ca_system_score_gemma":0.000007703165,"threshold_uncertainty_score":0.19421199},"labels":[],"label_agreement":null},{"id":"W3016640228","doi":"10.1177/2053951720919968","title":"How to translate artificial intelligence? Myths and justifications in public discourse","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Sociology; Performative utterance; Governmentality; Rhetorical question; Normative; Realm; Epistemology; Law; Politics; Political science","score_opus":0.4628728386934504,"score_gpt":0.4394201144088796,"score_spread":0.02345272428457079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016640228","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02826233,0.00023573465,0.0100942645,0.9583414,0.00028229662,0.00038560719,0.00042840646,0.00007384994,0.0018961068],"genre_scores_gemma":[0.9928527,0.0009816202,0.0014983917,0.0037267173,0.0007397467,0.00000827134,0.00009312594,0.0000108506765,0.00008856028],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985851,0.00011669827,0.00018418298,0.00040393946,0.0003430548,0.00036702742],"domain_scores_gemma":[0.99897313,0.00015029596,0.000048406946,0.00031116404,0.00009845546,0.0004185342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011694939,0.000101462334,0.00015043397,0.000020858159,0.00060393027,0.0008750687,0.00068363536,0.0001629185,0.00001931364],"category_scores_gemma":[0.0014185115,0.00010262047,0.000054336135,0.0006668698,0.0005050724,0.00085807143,0.00016953854,0.00031628404,0.000015991724],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009020096,0.00012572989,0.00030793922,0.000030608535,0.000039902854,0.0000035368773,0.45218047,0.0000037701163,0.00060515816,0.171794,0.024721077,0.3501788],"study_design_scores_gemma":[0.0001359264,0.00006761373,0.0014209329,0.000031956282,0.000053477565,2.9159477e-7,0.48474175,0.0013292528,0.00008447402,0.026189778,0.4853899,0.00055467756],"about_ca_topic_score_codex":0.000874344,"about_ca_topic_score_gemma":0.010267226,"teacher_disagreement_score":0.9645904,"about_ca_system_score_codex":0.00004020111,"about_ca_system_score_gemma":0.0003964397,"threshold_uncertainty_score":0.8438308},"labels":[],"label_agreement":null},{"id":"W3023430655","doi":"10.1177/2053951720919151","title":"A dialogic analysis of Hello Barbie’s conversations with children","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Dialogic; Sociology; Personalization; Rhetoric; Advertising; Computer science; Public relations; World Wide Web; Business; Pedagogy; Linguistics; Political science","score_opus":0.15811131274383994,"score_gpt":0.3285408846948391,"score_spread":0.17042957195099917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023430655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.790453,0.001843908,0.06921491,0.083551675,0.00017739563,0.0013082138,0.0034647996,0.00041480243,0.049571287],"genre_scores_gemma":[0.99519324,0.0007532166,0.0017357308,0.00056629186,0.00007513503,0.0000050429644,0.0016288126,0.0000035410783,0.00003899],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99917346,0.00011965129,0.00014951383,0.00018904477,0.00025779012,0.00011053123],"domain_scores_gemma":[0.9989691,0.00008991705,0.0001205877,0.00064766075,0.00009142396,0.00008131143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041893404,0.000053319018,0.00014122327,0.000025711532,0.0003202169,0.000056045512,0.0007644118,0.000058206107,0.00012184118],"category_scores_gemma":[0.00012339765,0.000045621025,0.00009496723,0.0016818088,0.00022163555,0.00029326955,0.00018305672,0.00008613996,0.000008269095],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002137072,0.0003934525,0.61188114,0.00001684745,0.006485797,3.842852e-7,0.19096819,0.0005127715,0.00020488861,0.051544648,0.11495555,0.02301496],"study_design_scores_gemma":[0.0008276018,0.000078545774,0.7332576,0.000011680417,0.0031402977,1.9758816e-7,0.046506975,0.026137788,0.000018252636,0.0003319701,0.18926361,0.0004254918],"about_ca_topic_score_codex":0.0026805229,"about_ca_topic_score_gemma":0.0014460894,"teacher_disagreement_score":0.20474023,"about_ca_system_score_codex":0.000026850756,"about_ca_system_score_gemma":0.00019371435,"threshold_uncertainty_score":0.40521666},"labels":[],"label_agreement":null},{"id":"W3026033602","doi":"10.1177/2053951720925853","title":"Big Data and surveillance: Hype, commercial logics and new intimate spheres","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Big data; Analytics; Variety (cybernetics); Service provider; Nexus (standard); Data science; Service (business); Scholarship; Public relations; Sociology; Internet privacy; Business; Computer science; Political science; Marketing","score_opus":0.3711333653075144,"score_gpt":0.32477500051252844,"score_spread":0.04635836479498595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026033602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6693626,0.028820235,0.1523298,0.100966476,0.012079056,0.0029106352,0.020309322,0.0022666089,0.010955279],"genre_scores_gemma":[0.93394005,0.0059035327,0.004123557,0.02388185,0.015026683,0.000002650906,0.01692209,0.00007997653,0.00011961842],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830973,0.000011734162,0.0002803126,0.0008260697,0.00025632165,0.00031583864],"domain_scores_gemma":[0.9983707,0.00006652955,0.00016621102,0.0012708093,0.00007295762,0.00005277738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036340914,0.0002499521,0.00030125937,0.000017272469,0.0002518955,0.00077476323,0.0016330273,0.000122068486,0.0001323695],"category_scores_gemma":[0.00034034858,0.00021701778,0.000028988496,0.00047257525,0.00021510519,0.0017288307,0.006798745,0.00021828998,0.00009724114],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002163703,0.000023993209,0.046862807,0.0002596749,0.000037522906,0.0000039193255,0.00006524527,7.5325397e-7,0.00009533826,0.00020933429,0.6405198,0.31189996],"study_design_scores_gemma":[0.0004184171,0.0000067595865,0.034682047,0.000031089672,0.000057397807,0.0000035172475,0.00049054174,0.013304029,0.000008509312,0.0003102868,0.950322,0.0003654569],"about_ca_topic_score_codex":0.0013778363,"about_ca_topic_score_gemma":0.0010422388,"teacher_disagreement_score":0.31153452,"about_ca_system_score_codex":0.0000061380156,"about_ca_system_score_gemma":0.00005344758,"threshold_uncertainty_score":0.8849728},"labels":[],"label_agreement":null},{"id":"W3035890329","doi":"10.1177/2053951720933930","title":"Doing nothing does something: Embodiment and data in the COVID-19 pandemic","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"Canada Research Chairs","keywords":"Nothing; Pandemic; Meaning (existential); Social distance; Boredom; Sociology; Obligation; Coronavirus disease 2019 (COVID-19); Embodied cognition; Epistemology; Political science; Law; Philosophy","score_opus":0.4596340014053394,"score_gpt":0.46556111470966155,"score_spread":0.0059271133043221624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035890329","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0925439,0.0025767484,0.0036681113,0.89343894,0.00078575476,0.00093729526,0.0014224026,0.00026583992,0.004360985],"genre_scores_gemma":[0.85490245,0.0065915943,0.003726673,0.13297248,0.0013910513,0.000004820007,0.00035793672,0.000016152562,0.00003682049],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977244,0.0004395833,0.00023372506,0.0005579309,0.00066771766,0.00037660485],"domain_scores_gemma":[0.997274,0.0014176851,0.00011172159,0.00087688694,0.00003564274,0.00028408345],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008929384,0.0001213115,0.0001832831,0.000011580409,0.0013194671,0.0006701801,0.0024544247,0.00020311764,0.000018509674],"category_scores_gemma":[0.00475058,0.00008221522,0.000042481246,0.00032511778,0.00051240664,0.0011208281,0.0015614827,0.00068016164,0.0000049017203],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065983727,0.000040376217,0.0116397515,0.000077134726,0.00004944452,0.000007711539,0.92770064,0.0000028989293,0.000159149,0.0054413467,0.043806538,0.011068431],"study_design_scores_gemma":[0.000299956,0.000011959222,0.00047264862,0.000015542471,0.000029011067,6.53719e-7,0.13636017,0.00035325403,0.0000013654807,0.00268514,0.8596039,0.00016641727],"about_ca_topic_score_codex":0.0140808,"about_ca_topic_score_gemma":0.008348437,"teacher_disagreement_score":0.8157973,"about_ca_system_score_codex":0.000101201185,"about_ca_system_score_gemma":0.0006960436,"threshold_uncertainty_score":0.9999807},"labels":[],"label_agreement":null},{"id":"W3036150657","doi":"10.1177/2053951720935143","title":"Personalization as a promise: Can Big Data change the practice of insurance?","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Big data; Data science; Pooling; Personalization; Telematics; Computer science; Analytics; Data mining; Artificial intelligence; World Wide Web","score_opus":0.6585193461766956,"score_gpt":0.4307756542434794,"score_spread":0.2277436919332162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036150657","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03406731,0.007471021,0.045999285,0.8060657,0.0010547407,0.0034238966,0.099564604,0.00054453744,0.0018089279],"genre_scores_gemma":[0.9710442,0.003902538,0.0070332936,0.0113216555,0.0009766662,0.00009324613,0.0055080284,0.00002314883,0.00009722438],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973727,0.00010792034,0.00042731993,0.00087347755,0.0010145049,0.00020407683],"domain_scores_gemma":[0.9935889,0.00070657564,0.0004696566,0.00489326,0.00026267656,0.000078902325],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0018487653,0.00013245767,0.0002038236,0.000017125054,0.0003016113,0.00021716458,0.007332259,0.000115963325,0.000040776544],"category_scores_gemma":[0.007829034,0.000082814804,0.00005655404,0.0016098198,0.00031993538,0.00090845214,0.0045319647,0.00023704165,0.00009031744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015528492,0.000084976666,0.00081881246,0.000021280337,0.00004748676,0.0000010551502,0.0036277326,7.040265e-7,0.0005016452,0.0013054475,0.6086323,0.38494298],"study_design_scores_gemma":[0.00020857136,0.000029622042,0.0021763025,0.000011023911,0.00003602146,0.0000049663026,0.011693812,0.0046820957,0.00010819692,0.00050951587,0.98042524,0.000114605464],"about_ca_topic_score_codex":0.00086676766,"about_ca_topic_score_gemma":0.00017348975,"teacher_disagreement_score":0.9369769,"about_ca_system_score_codex":0.000017011009,"about_ca_system_score_gemma":0.0001870829,"threshold_uncertainty_score":0.99803853},"labels":[],"label_agreement":null},{"id":"W3037873118","doi":"10.1177/2053951720935615","title":"Sunlight alone is not a disinfectant: Consent and the futility of opening Big Data black boxes (without assistance)","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Transparency (behavior); Internet privacy; Big data; Context (archaeology); Reputation; Computer science; Deliverable; Fallacy; Data science; Public relations; Computer security; Political science; Law; Engineering; Epistemology; Data mining","score_opus":0.3987993905371733,"score_gpt":0.4096981178991782,"score_spread":0.010898727362004923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037873118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48781034,0.003956775,0.002181391,0.47480705,0.0012458836,0.0017009365,0.014164455,0.0001891455,0.013944008],"genre_scores_gemma":[0.98430586,0.0066502956,0.0004981851,0.007295283,0.0008673863,0.0000021315566,0.00024652993,0.000015185158,0.00011916863],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973453,0.00044335533,0.00039423123,0.0006540603,0.0007679768,0.0003950756],"domain_scores_gemma":[0.996797,0.0011057177,0.0002826689,0.0013673126,0.00019503462,0.0002522501],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004427366,0.00018109611,0.000464093,0.0000072311095,0.0010577124,0.0004397778,0.0019452617,0.00020291304,0.000037714686],"category_scores_gemma":[0.0034036255,0.00013118201,0.000115946066,0.0003521915,0.0036093756,0.0006489737,0.0020494366,0.0004301688,0.000007764668],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044692875,0.0002572143,0.029132742,0.00042198872,0.0008465231,0.0000075576336,0.54110426,5.8245075e-7,0.0011661344,0.01740365,0.3854002,0.02381223],"study_design_scores_gemma":[0.0055401437,0.00011513274,0.03314774,0.0002871454,0.00068377564,0.000001388341,0.111324765,0.0029224595,0.0006300668,0.005396466,0.8388825,0.0010684216],"about_ca_topic_score_codex":0.010028585,"about_ca_topic_score_gemma":0.011003992,"teacher_disagreement_score":0.4964955,"about_ca_system_score_codex":0.000038809347,"about_ca_system_score_gemma":0.0007943456,"threshold_uncertainty_score":0.99910223},"labels":[],"label_agreement":null},{"id":"W3045420183","doi":"10.1177/2053951720938405","title":"Going viral: How a single tweet spawned a COVID-19 conspiracy theory on Twitter","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":216,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Canadian Institutes of Health Research","keywords":"Misinformation; Social media; Hoax; Disinformation; Coronavirus disease 2019 (COVID-19); Politics; Pandemic; Power (physics); Fake news; Media studies; Internet privacy; Vetting; Political science; Flagging; Public relations; Sociology; Law; Computer science; History; Medicine","score_opus":0.36149471297421987,"score_gpt":0.38132512283647607,"score_spread":0.019830409862256204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045420183","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22580303,0.0005649375,0.050182644,0.5678055,0.0020466151,0.002439662,0.0028908295,0.0021072235,0.14615954],"genre_scores_gemma":[0.82081866,0.00012130645,0.0008242809,0.17608921,0.0008352072,0.0000021725875,0.00033961667,0.000016568498,0.0009529645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983868,0.00023553651,0.00018465605,0.00030726768,0.00051227165,0.00037345954],"domain_scores_gemma":[0.9984098,0.0003579926,0.00015073777,0.00049791776,0.000040077102,0.0005434724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013189525,0.00014123236,0.00016809038,0.000017057517,0.00063475437,0.00044763615,0.00072609814,0.00012232873,0.0004153902],"category_scores_gemma":[0.0032660568,0.00012486894,0.000104021085,0.00031085804,0.0003004876,0.0008614465,0.00025273807,0.00019450707,0.0003249572],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003314312,0.000048455142,0.00010349757,0.000039787443,0.000034766395,0.0000028465904,0.17224446,0.0000029420098,0.0003029423,0.0067408504,0.8115421,0.008904246],"study_design_scores_gemma":[0.0005760552,0.00006156794,0.00011539103,0.000015459638,0.00001723545,5.6027295e-7,0.03269194,0.00026772032,0.00006951306,0.00046268388,0.9655346,0.00018725506],"about_ca_topic_score_codex":0.00013663546,"about_ca_topic_score_gemma":0.000061679544,"teacher_disagreement_score":0.59501565,"about_ca_system_score_codex":0.00014981866,"about_ca_system_score_gemma":0.00057192106,"threshold_uncertainty_score":0.50920075},"labels":[],"label_agreement":null},{"id":"W3107637603","doi":"10.1177/2053951720971009","title":"Viral Data","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"COVID-19 Digital Contact Tracing","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Biopower; Pandemic; Misinformation; Ideology; Big data; Sociology; Coronavirus disease 2019 (COVID-19); Disinformation; 2019-20 coronavirus outbreak; Data collection; Criminology; Political science; Media studies; Politics; Law; Virology; Social science; Social media; Computer science; Biology","score_opus":0.31391119185134614,"score_gpt":0.33245404400687417,"score_spread":0.018542852155528033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107637603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002056115,0.00042136744,0.9728146,0.021107187,0.00053366995,0.00018100812,0.0012812861,0.00062452897,0.0009801934],"genre_scores_gemma":[0.91026926,0.00007169017,0.053605158,0.033302486,0.00093344104,0.0000028638965,0.0017250548,0.000022865783,0.000067200286],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981613,0.000025769108,0.00019196421,0.0009843623,0.00034790972,0.00028866946],"domain_scores_gemma":[0.99542814,0.00012625089,0.000059810718,0.004185138,0.0000266677,0.00017397323],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003110175,0.00013667413,0.0001442309,0.0000073539522,0.00011484754,0.0005201943,0.008701757,0.000051142193,0.000006625301],"category_scores_gemma":[0.00024965956,0.00013427871,0.00005616562,0.0003470372,0.000037134752,0.003356192,0.012095802,0.00019069105,0.00020148442],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059973195,0.00007386933,0.0007654714,0.0001256669,0.00009222641,0.000037826976,0.0030125675,0.000009432356,0.0020310185,0.004047664,0.73235136,0.2574469],"study_design_scores_gemma":[0.00035429164,0.000037801437,0.0012031067,0.000018698629,0.00001384423,0.0000036453064,0.00008790877,0.3012522,0.00017339765,0.0002110748,0.69633454,0.00030950288],"about_ca_topic_score_codex":0.00007942547,"about_ca_topic_score_gemma":0.00002186966,"teacher_disagreement_score":0.9192095,"about_ca_system_score_codex":0.00003581377,"about_ca_system_score_gemma":0.00024824057,"threshold_uncertainty_score":0.99666166},"labels":[],"label_agreement":null},{"id":"W3125368128","doi":"10.1177/2053951715608876","title":"Big Data and <i>The Phantom Public</i> : Walter Lippmann and the fallacy of data privacy self-management","year":2015,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Fallacy; Data governance; Sociology; Civil liberties; Information privacy; Law and economics; Political science; Law; Public administration; Economics; Politics; Data quality; Epistemology; Philosophy","score_opus":0.19243867076290644,"score_gpt":0.3410098696110038,"score_spread":0.14857119884809739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125368128","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09893567,0.098094516,0.07752798,0.5598972,0.015435396,0.023685653,0.067681365,0.0019796875,0.056762565],"genre_scores_gemma":[0.8892011,0.07926147,0.009674777,0.0042362185,0.004987669,0.00007653569,0.01187166,0.000060722272,0.0006298508],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996845,0.0006442742,0.00037390194,0.0009140662,0.000808491,0.000414245],"domain_scores_gemma":[0.9923595,0.00039928965,0.00024982076,0.0066831396,0.000116301715,0.00019195133],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.010686091,0.00019439269,0.0003010674,0.000026316411,0.0008604218,0.0006592032,0.008562478,0.00011445478,0.000009546159],"category_scores_gemma":[0.0016392063,0.0001203649,0.00004003913,0.00044946777,0.0016380885,0.0025670382,0.02739188,0.00026084483,0.000012189419],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014410293,0.0001886196,0.0008639249,0.00013513333,0.00038927468,0.0000019852116,0.03553716,4.5160128e-8,0.0000055185656,0.009073571,0.8243421,0.12931858],"study_design_scores_gemma":[0.0038506277,0.000013270005,0.00021463356,0.000019700828,0.00019774374,0.000004526214,0.010902251,0.002611617,0.000002251085,0.0040447037,0.97796077,0.0001778866],"about_ca_topic_score_codex":0.005765249,"about_ca_topic_score_gemma":0.0024261281,"teacher_disagreement_score":0.79026544,"about_ca_system_score_codex":0.000043671,"about_ca_system_score_gemma":0.00029289475,"threshold_uncertainty_score":0.9968017},"labels":[],"label_agreement":null},{"id":"W3128452488","doi":"10.1177/2053951720978991","title":"The cancer multiple: Producing and translating genomic big data into oncology care","year":2021,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Simon Fraser University; Genome Canada","keywords":"Big data; CONTEST; Personalized medicine; Data science; Computer science; Bioinformatics; Biology; Political science","score_opus":0.08270260390087346,"score_gpt":0.3221955651368332,"score_spread":0.2394929612359597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128452488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75548404,0.23186691,0.0019406801,0.0037778893,0.0020384078,0.00039298815,0.0043170666,0.000018673627,0.0001633606],"genre_scores_gemma":[0.9305546,0.052865397,0.004539579,0.0010071318,0.00278604,0.000026255879,0.008124609,0.00003754236,0.000058795842],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857986,0.000047334095,0.00020163697,0.0008444583,0.00008322963,0.00024347445],"domain_scores_gemma":[0.99767596,0.00007709799,0.000079144396,0.0020044115,0.00009334342,0.0000700491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027140716,0.00013837687,0.00013973344,0.0000041941307,0.00037303404,0.00009094373,0.00078232196,0.00013361426,0.0000019634977],"category_scores_gemma":[0.00030088922,0.000119102966,0.00004369436,0.000073026495,0.00013327943,0.0000062275335,0.002050088,0.00013914393,0.0000010592155],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022552544,0.000025290403,0.00380606,0.00007839877,0.00015900694,0.000004133599,0.0037613166,0.0000362028,0.3583074,0.0000042243955,0.02792903,0.6058664],"study_design_scores_gemma":[0.00072862837,0.000043931963,0.003012259,0.000021316635,0.000090443646,0.000010862893,0.0058660214,0.0010187533,0.013390349,0.000018751996,0.97555727,0.00024142776],"about_ca_topic_score_codex":0.00080096046,"about_ca_topic_score_gemma":0.02771241,"teacher_disagreement_score":0.9476282,"about_ca_system_score_codex":0.000055853707,"about_ca_system_score_gemma":0.00090151315,"threshold_uncertainty_score":0.9900293},"labels":[],"label_agreement":null},{"id":"W3163624904","doi":"10.1177/20539517211017308","title":"Data as asset? The measurement, governance, and valuation of digital personal data by Big Tech","year":2021,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":297,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Big data; Business; Economics; Corporate governance; Valuation (finance); Finance; Computer science","score_opus":0.2878700729135893,"score_gpt":0.3537727177091816,"score_spread":0.06590264479559232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163624904","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09718089,0.058137126,0.041884925,0.06726681,0.006309207,0.0038407494,0.6966152,0.0005031517,0.028261954],"genre_scores_gemma":[0.9361059,0.012173388,0.00085526693,0.00047147853,0.0013217867,0.000011106995,0.04877186,0.000021811573,0.0002674081],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972143,0.00016957153,0.00023272849,0.0007664003,0.001369462,0.0002475385],"domain_scores_gemma":[0.9961816,0.00012729247,0.00020300118,0.0032125055,0.00019901426,0.000076550234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038791646,0.00012315919,0.0001506011,0.0000064722467,0.00065715786,0.00043718584,0.0034215567,0.000117080825,0.0000470846],"category_scores_gemma":[0.0039003484,0.00010368662,0.000032974323,0.0003848804,0.00039681295,0.0023011148,0.0062726913,0.0002165328,0.000012962255],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012503399,0.00017425898,0.0017580554,0.00004458272,0.00013630334,0.0000012540603,0.003012648,3.9332154e-8,0.001292021,0.0005521711,0.85410815,0.13890798],"study_design_scores_gemma":[0.00037771105,0.000017167438,0.0022956491,0.000035133115,0.00009721331,0.0000050866856,0.008130285,0.0014521803,0.00012908934,0.0016087658,0.9856716,0.00018016563],"about_ca_topic_score_codex":0.0029492623,"about_ca_topic_score_gemma":0.004353998,"teacher_disagreement_score":0.838925,"about_ca_system_score_codex":0.00008559768,"about_ca_system_score_gemma":0.0008876619,"threshold_uncertainty_score":0.7818461},"labels":[],"label_agreement":null},{"id":"W3164866704","doi":"10.1177/20539517211019441","title":"COVID-19, digital health technology and the politics of the unprecedented","year":2021,"lang":"en","type":"article","venue":"Big Data & Society","topic":"COVID-19 Digital Contact Tracing","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; York University","funders":"","keywords":"Public health; Context (archaeology); Politics; Pandemic; Digital health; Political science; Corporate governance; Health technology; Global health; Biopower; Political economy; Coronavirus disease 2019 (COVID-19); Emerging technologies; Health care; Sociology; Economic growth; Economics; Medicine; Computer science; Geography; Law","score_opus":0.08789097473759842,"score_gpt":0.32847936124222454,"score_spread":0.2405883865046261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164866704","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036301322,0.0062373704,0.4573337,0.49589008,0.0008701537,0.00080090103,0.0013203752,0.00046520043,0.0007808666],"genre_scores_gemma":[0.97996765,0.00014878347,0.0014094972,0.018190235,0.000047436413,0.000004112278,0.000045726778,0.00000777748,0.00017879184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869984,0.000070993345,0.00025903364,0.00042222816,0.00026974487,0.00027813975],"domain_scores_gemma":[0.99698496,0.0005358493,0.00014404509,0.0021303047,0.00007462968,0.00013023992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004307119,0.00011092852,0.00019340756,0.000022151517,0.00034632554,0.00028556192,0.0020900662,0.000062872554,0.00000132679],"category_scores_gemma":[0.0014723082,0.00007019988,0.00009005598,0.00091723516,0.00044513168,0.00048200676,0.004196529,0.00019964171,0.0000020128252],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013848927,0.00027263662,0.013847571,0.0007012556,0.00031422055,0.000015771713,0.01129528,0.000026149255,0.00034288378,0.8226974,0.060210504,0.09026245],"study_design_scores_gemma":[0.0064528156,0.00012942139,0.00881777,0.00031017035,0.00006778213,0.00038753045,0.009023065,0.03410787,0.0018199708,0.0795701,0.8584828,0.0008307185],"about_ca_topic_score_codex":0.00015483992,"about_ca_topic_score_gemma":0.00011494007,"teacher_disagreement_score":0.94366634,"about_ca_system_score_codex":0.00013476613,"about_ca_system_score_gemma":0.0018920886,"threshold_uncertainty_score":0.5230673},"labels":[],"label_agreement":null},{"id":"W3171456393","doi":"10.1177/20539517211021115","title":"Studying the COVID-19 infodemic at scale","year":2021,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Canadian Institutes of Health Research","keywords":"Big data; Coronavirus disease 2019 (COVID-19); Data science; Theme (computing); Social media; 2019-20 coronavirus outbreak; Scale (ratio); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Sociology; Medicine; Data mining; World Wide Web","score_opus":0.33837362190386217,"score_gpt":0.40819520606475285,"score_spread":0.06982158416089068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171456393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63198686,0.0032705304,0.0060605216,0.1537851,0.0036625317,0.0011906287,0.001402116,0.0006872274,0.1979545],"genre_scores_gemma":[0.8582286,0.0054699616,0.001212053,0.111779995,0.0015122605,0.000005868691,0.0010075669,0.000019423944,0.020764276],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987992,0.0001411432,0.00016616778,0.0001656685,0.0004677731,0.00026004887],"domain_scores_gemma":[0.9987444,0.0002236186,0.000078503675,0.00067406474,0.000060737246,0.00021865837],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0016876748,0.00006803259,0.000084940606,0.000005967243,0.0015806543,0.00019257757,0.00067704177,0.000075923854,0.00062249915],"category_scores_gemma":[0.0013295319,0.000050570765,0.00006487414,0.0003541282,0.00022426448,0.00048764475,0.0006390446,0.00012715958,0.00019697493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014848121,0.0000137086545,0.0011860883,0.000009781306,0.00001585842,6.1329905e-7,0.16036716,0.0000044074977,0.000057312627,0.00043481452,0.83102226,0.0068865106],"study_design_scores_gemma":[0.00018009813,0.0000021821145,0.0012558068,0.0000034905813,0.000010423026,0.0000023458724,0.086148866,0.00012209613,0.000022372114,0.00007294427,0.9121066,0.000072827475],"about_ca_topic_score_codex":0.0008582893,"about_ca_topic_score_gemma":0.0042713103,"teacher_disagreement_score":0.22624174,"about_ca_system_score_codex":0.00024070566,"about_ca_system_score_gemma":0.0009653475,"threshold_uncertainty_score":0.99971914},"labels":[],"label_agreement":null},{"id":"W3185692625","doi":"10.1177/20539517221082027","title":"Diversity in sociotechnical machine learning systems","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Diversity (politics); Sociotechnical system; Context (archaeology); Epistemology; Computer science; Sociocultural evolution; Knowledge management; Sociology; Management science; Data science; Artificial intelligence; Engineering","score_opus":0.30243287312393025,"score_gpt":0.3858965764881999,"score_spread":0.08346370336426967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185692625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88481164,0.0051510334,0.0006288537,0.06291271,0.0045707864,0.0014040675,0.0017093719,0.000839369,0.037972167],"genre_scores_gemma":[0.99653083,0.0010471148,0.00008211768,0.00072085107,0.00034860894,0.0000064339324,0.00017988386,0.000008895015,0.001075248],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978785,0.0005070189,0.00016135201,0.00030780135,0.0007744995,0.0003708581],"domain_scores_gemma":[0.9991572,0.0002634154,0.00009186061,0.00032788736,0.000049308746,0.000110342975],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0053555095,0.00008318087,0.00016682915,0.000019285508,0.0071177143,0.00010817378,0.0012214794,0.00016250166,0.00006544658],"category_scores_gemma":[0.0005893536,0.00009459511,0.00009251074,0.00038271202,0.00028869064,0.00033467537,0.005588903,0.0012365881,0.0000070625993],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003866959,0.00064373075,0.14686646,0.00008068924,0.00018104013,0.000057105077,0.5277849,0.00073249463,0.00015954814,0.0615834,0.25332016,0.00855182],"study_design_scores_gemma":[0.0004641363,0.00005093302,0.0050007724,0.0000118026655,0.000022317869,8.575751e-7,0.092775926,0.0024366134,6.197998e-7,0.0019109969,0.8970341,0.00029094302],"about_ca_topic_score_codex":0.060299598,"about_ca_topic_score_gemma":0.0049097817,"teacher_disagreement_score":0.64371395,"about_ca_system_score_codex":0.00048582075,"about_ca_system_score_gemma":0.00038276118,"threshold_uncertainty_score":0.9941749},"labels":[],"label_agreement":null},{"id":"W3198590727","doi":"10.1177/20539517211039493","title":"Towards a United Nations Internal Regulation for Artificial Intelligence","year":2021,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Set (abstract data type); Work (physics); Commission; Artificial intelligence; Sociology; Symbolic artificial intelligence; Political science; Law; Computer science; Engineering; Artificial Intelligence System","score_opus":0.41570144128799846,"score_gpt":0.45784185557803503,"score_spread":0.042140414290036565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198590727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028034706,0.0006263823,0.6839001,0.21160418,0.0055213263,0.0011798617,0.003072268,0.00041168256,0.0656495],"genre_scores_gemma":[0.9657067,0.0024892075,0.021346036,0.002653264,0.003050362,0.000019466073,0.0024258266,0.000021958964,0.002287196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875164,0.0001177202,0.00021472549,0.00027285307,0.00038942235,0.0002536105],"domain_scores_gemma":[0.99829555,0.0003787417,0.00008798102,0.0003512615,0.0007781172,0.000108365544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015417688,0.000077138255,0.00010444347,0.00006412703,0.0011201844,0.00038971085,0.0004955465,0.00018769295,0.00009858892],"category_scores_gemma":[0.0037178693,0.000083835286,0.00011664434,0.0013397539,0.00027274172,0.00048252387,0.00020575765,0.00018329894,0.000010909931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010498062,0.00013475644,0.0000468811,0.000027615128,0.00007564086,0.0000013686312,0.050263587,0.000012881582,0.0005648334,0.80504,0.054423258,0.0893987],"study_design_scores_gemma":[0.000093754614,0.000024202642,0.00047840583,0.000052275365,0.00004737593,6.1680953e-7,0.039462008,0.0046867845,0.0007751623,0.18383375,0.7703175,0.00022816026],"about_ca_topic_score_codex":0.0034018552,"about_ca_topic_score_gemma":0.013167074,"teacher_disagreement_score":0.93767196,"about_ca_system_score_codex":0.00010190096,"about_ca_system_score_gemma":0.0008869407,"threshold_uncertainty_score":0.8615666},"labels":[],"label_agreement":null},{"id":"W4205467669","doi":"10.1177/20539517211065248","title":"Co-design and ethical artificial intelligence for health: An agenda for critical research and practice","year":2021,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; Public Health Ontario; University of Toronto","funders":"","keywords":"Normative; Health care; Engineering ethics; Digital health; Research design; Management science; Psychology; Knowledge management; Computer science; Sociology; Political science; Engineering; Social science","score_opus":0.8442446932799106,"score_gpt":0.659323485598134,"score_spread":0.18492120768177656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205467669","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075248536,0.0016277933,0.2857247,0.70874286,0.0005102372,0.0011374748,0.00088722835,0.000056705616,0.00056051975],"genre_scores_gemma":[0.40839753,0.016907852,0.5168285,0.050828688,0.0056459983,0.00015997763,0.00081383716,0.00008077215,0.0003368687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964973,0.0014040218,0.0002686967,0.0005805577,0.00061758846,0.0006318576],"domain_scores_gemma":[0.974959,0.022946492,0.000055953205,0.00037502678,0.0012587139,0.00040480573],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.02490784,0.00009568681,0.00020586068,0.000015035911,0.0032503353,0.00090573647,0.0003661392,0.0005060133,0.00001036685],"category_scores_gemma":[0.059975855,0.00010080333,0.000046324214,0.00022118258,0.0019015878,0.0005908401,0.00018344198,0.000840654,0.000001791687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013333779,0.0002599445,0.0000054770835,0.00016255918,0.000039574457,0.000003410688,0.092679024,3.5604097e-7,0.00045136912,0.69514674,0.13055146,0.08056672],"study_design_scores_gemma":[0.00015914968,0.00067917147,0.000030318066,0.00005022851,0.00003237739,0.000004248385,0.17535062,0.0015108099,0.00034547606,0.40525487,0.41633078,0.0002519491],"about_ca_topic_score_codex":0.00092171744,"about_ca_topic_score_gemma":0.0017198051,"teacher_disagreement_score":0.65791416,"about_ca_system_score_codex":0.00007970832,"about_ca_system_score_gemma":0.00216693,"threshold_uncertainty_score":0.9980473},"labels":[],"label_agreement":null},{"id":"W4225591722","doi":"10.1177/20539517221087855","title":"Co-designing algorithms for governance: Ensuring responsible and accountable algorithmic management of refugee camp supplies","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Grand Challenges Canada","keywords":"Scrutiny; Algorithm; Refugee; Accountability; Discretion; Computer science; Corporate governance; Transparency (behavior); Big data; Computer security; Law; Political science; Economics; Data mining","score_opus":0.15784966433016084,"score_gpt":0.3928410288559661,"score_spread":0.23499136452580527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225591722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69585204,0.034601543,0.03587173,0.064498454,0.010921612,0.016352871,0.06463125,0.0013890202,0.07588147],"genre_scores_gemma":[0.82683504,0.023915155,0.13352042,0.0017893623,0.0016650503,0.00028090546,0.0011530869,0.00012297396,0.010717988],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980209,0.00013917082,0.00025030837,0.00040383625,0.0007388059,0.0004469911],"domain_scores_gemma":[0.99876183,0.00039184798,0.00020431115,0.00044350768,0.00010925639,0.00008921941],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0045619425,0.00012659476,0.0002314172,0.000018256802,0.0020303093,0.00017398907,0.00075490755,0.00009748104,0.00005359715],"category_scores_gemma":[0.00013374462,0.00014212892,0.00008642559,0.00027302338,0.0003340195,0.00050560036,0.0006027767,0.0002649143,0.0000015263886],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030397912,0.0005334359,0.0017028063,0.0010860346,0.001277477,0.000026382437,0.1972357,0.00008875615,0.0057820235,0.1602722,0.4781312,0.15356001],"study_design_scores_gemma":[0.001061987,0.000108036766,0.001289863,0.000064523294,0.00009973212,0.0000013077995,0.11155023,0.0004197724,0.00064432615,0.008539464,0.875845,0.00037573825],"about_ca_topic_score_codex":0.002123379,"about_ca_topic_score_gemma":0.00025552948,"teacher_disagreement_score":0.3977138,"about_ca_system_score_codex":0.00023302725,"about_ca_system_score_gemma":0.0003987816,"threshold_uncertainty_score":0.9992689},"labels":[],"label_agreement":null},{"id":"W4225867554","doi":"10.1177/20539517221089310","title":"Datafication and the practice of intelligence production","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Policing Practices and Perceptions","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Wilfrid Laurier University","funders":"University of New South Wales","keywords":"Dominance (genetics); Politics; Sociology; Public relations; Intelligence analysis; Political science; Knowledge production; Knowledge management; Law; Computer science","score_opus":0.24128517250840026,"score_gpt":0.43083080678363944,"score_spread":0.18954563427523918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225867554","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19800106,0.004655754,0.022894133,0.6903607,0.007877137,0.0042092125,0.00307575,0.00037045864,0.06855576],"genre_scores_gemma":[0.9894766,0.00685947,0.0016104168,0.00085707504,0.00044607584,0.000022217007,0.00017311714,0.000004074737,0.0005509551],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893785,0.0004364827,0.00011000379,0.00016821157,0.00026252153,0.0000849361],"domain_scores_gemma":[0.9987875,0.00047408382,0.00016025649,0.00050786836,0.000049696762,0.00002056149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039488054,0.000031800508,0.0000506515,0.0000066545326,0.0011315015,0.000040693285,0.00044433193,0.000016267706,0.000060912207],"category_scores_gemma":[0.0011412285,0.00002534244,0.000019460329,0.00025873506,0.00041176277,0.0005828088,0.00040377854,0.00014630357,0.00000385839],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010194718,0.00024994972,0.0004125707,0.000026628466,0.000086517175,1.2311514e-7,0.5857203,0.00009817786,0.00042405428,0.059526503,0.15176369,0.20158955],"study_design_scores_gemma":[0.00005415491,0.0000076734295,0.00050758437,0.0000017846738,0.00004396573,0.0000026607627,0.12310655,0.0003321814,0.0000065152312,0.0002946151,0.8756069,0.000035419853],"about_ca_topic_score_codex":0.029265918,"about_ca_topic_score_gemma":0.001326941,"teacher_disagreement_score":0.79147553,"about_ca_system_score_codex":0.000030409381,"about_ca_system_score_gemma":0.000105126506,"threshold_uncertainty_score":0.9771983},"labels":[],"label_agreement":null},{"id":"W4285098881","doi":"10.1177/20539517221112925","title":"A comparative analysis of data governance: Socio-technical imaginaries of digital personal data in the USA and EU (2008–2016)","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Context (archaeology); Corporate governance; Data governance; Commercialization; Data Protection Act 1998; Asset (computer security); Big data; Governmentality; Sociology; Politics; Technoscience; Political science; Public relations; Economics; Social science; Law; Economy; Computer security; Computer science; Data quality; Management","score_opus":0.1642921433621306,"score_gpt":0.37651035585386755,"score_spread":0.21221821249173695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285098881","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43423152,0.010161383,0.0042576473,0.017388841,0.00048280787,0.0016267672,0.5281948,0.000082516744,0.0035737073],"genre_scores_gemma":[0.98273605,0.0012731616,0.0006436836,0.00014070298,0.000108266984,0.000010346592,0.0150609845,0.00000389612,0.000022920094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99763775,0.00032031658,0.0003060648,0.0006266264,0.00087523635,0.00023403505],"domain_scores_gemma":[0.9967517,0.0003876507,0.00027844534,0.002487834,0.000051146795,0.000043211217],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003060212,0.000113671245,0.00034695858,0.00003136912,0.00060903037,0.00013943017,0.0054339156,0.00006040078,0.00011841135],"category_scores_gemma":[0.0005796995,0.00009574704,0.00006451258,0.0011814036,0.0013344737,0.002125587,0.010334819,0.0003407611,0.000001356468],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016143812,0.0013621922,0.14977121,0.000098939156,0.0013006795,0.000009132885,0.13271074,0.0000041654694,0.00027764964,0.0063485303,0.69579655,0.012158752],"study_design_scores_gemma":[0.0010042514,0.00011894585,0.23366179,0.000025137775,0.001045764,0.000010577406,0.16948946,0.014487964,0.0000065282848,0.0011708775,0.57849085,0.00048785761],"about_ca_topic_score_codex":0.012408348,"about_ca_topic_score_gemma":0.01218049,"teacher_disagreement_score":0.54850453,"about_ca_system_score_codex":0.00008141523,"about_ca_system_score_gemma":0.0004395839,"threshold_uncertainty_score":0.9999472},"labels":[],"label_agreement":null},{"id":"W4293208778","doi":"10.1177/20539517221106381","title":"“Make our communities better through data”: The moral economy of smart city labor","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Smart Cities and Technologies","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Calgary Institute for the Humanities, University of Calgary; Social Sciences and Humanities Research Council of Canada; Andrew W. Mellon Foundation","keywords":"Moral economy; Smart city; Capitalism; Sociology; Mandate; Politics; Political economy; Context (archaeology); Political science; Internet privacy; Law","score_opus":0.15613239471174523,"score_gpt":0.2683254251344617,"score_spread":0.1121930304227165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293208778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9282538,0.0044522504,0.0014992474,0.015362931,0.002419836,0.0005630283,0.03997374,0.0013650003,0.006110117],"genre_scores_gemma":[0.9934051,0.0004185265,0.0017529246,0.0014734326,0.0001819958,0.000035753405,0.0026497946,0.000026076455,0.000056366775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927866,0.00003496542,0.00018830168,0.00015682598,0.00012564207,0.00021560809],"domain_scores_gemma":[0.99701774,0.00008198321,0.00004551007,0.002826258,0.000017233044,0.000011254821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033252963,0.00012717844,0.00017544972,0.000009686054,0.00031623448,0.000045119537,0.0025935904,0.000051747087,0.000051010025],"category_scores_gemma":[0.000011192209,0.000105718034,0.000055918725,0.00014695775,0.00012958041,0.00026668803,0.004253166,0.00042385806,0.000003710508],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038543076,0.00003398223,0.010604258,0.00008073063,0.0002751419,0.0000012927924,0.0029155763,0.00019963691,0.000026565398,0.0013438301,0.97815,0.006365118],"study_design_scores_gemma":[0.00021037523,0.000020247275,0.0026486008,0.0000066140715,0.00003435983,0.000004406568,0.053675782,0.008270534,0.00017977552,0.0013150354,0.93345857,0.00017568149],"about_ca_topic_score_codex":0.00077744655,"about_ca_topic_score_gemma":0.00034299184,"teacher_disagreement_score":0.06515128,"about_ca_system_score_codex":0.000038528193,"about_ca_system_score_gemma":0.000026302949,"threshold_uncertainty_score":0.5301267},"labels":[],"label_agreement":null},{"id":"W4312338894","doi":"10.1177/20539517221139785","title":"Politics of data reuse in machine learning systems: Theorizing reuse entanglements","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Research Data Management Practices","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Danmarks Frie Forskningsfond; Simon Fraser University; Concordia University; Copenhagen Business School","keywords":"Reuse; Politics; Sociology; Epistemology; Computer science; Data science; Political science; Engineering; Law","score_opus":0.3213972372293789,"score_gpt":0.39222555209141985,"score_spread":0.07082831486204094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312338894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16247058,0.028803067,0.6720283,0.047539245,0.00807116,0.007946533,0.064116366,0.0017572873,0.00726745],"genre_scores_gemma":[0.7973664,0.010110109,0.16398956,0.000947223,0.0004633428,0.000110090994,0.024669966,0.000089039844,0.0022542782],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99577045,0.00092836,0.00051101006,0.0010292082,0.0012383938,0.000522565],"domain_scores_gemma":[0.98086363,0.000507585,0.00036764148,0.018127438,0.000045270102,0.00008846092],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007923241,0.00015385475,0.00022822732,0.00011375853,0.00041885657,0.00083100295,0.041951705,0.000030514077,0.000017120557],"category_scores_gemma":[0.0031108125,0.00015836793,0.00003678504,0.0009799665,0.00007015096,0.01719452,0.15169984,0.0006401626,0.0000072775542],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008740062,0.0025560057,0.068079405,0.0017484674,0.0014001707,0.00047265794,0.016296718,0.0020720894,0.0032093555,0.26370144,0.611672,0.028704299],"study_design_scores_gemma":[0.00072811375,0.00008986551,0.0005299768,0.00004690794,0.000025359057,0.000009382713,0.00405652,0.22562803,0.000023726534,0.00045871115,0.7681661,0.00023728378],"about_ca_topic_score_codex":0.0026774134,"about_ca_topic_score_gemma":0.0000563431,"teacher_disagreement_score":0.6348958,"about_ca_system_score_codex":0.00019367834,"about_ca_system_score_gemma":0.00018600427,"threshold_uncertainty_score":0.99655145},"labels":[],"label_agreement":null},{"id":"W4312661347","doi":"10.1177/20539517221123304","title":"States of computing: On government organization and artificial intelligence in Canada","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Political and Social Dynamics in Chile and Latin America","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"Social Sciences and Humanities Research Council of Canada; Fonds de Recherche du Québec-Société et Culture","keywords":"Bureaucracy; Sociology; Vision; Government (linguistics); Politics; Context (archaeology); Big data; Artificial intelligence; Political science; Law; Computer science","score_opus":0.058461279178372245,"score_gpt":0.2973323335144453,"score_spread":0.23887105433607309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312661347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884767,0.00006405845,0.0021538488,0.0027001288,0.00055651437,0.00018928404,0.0015472868,0.000016757396,0.004295438],"genre_scores_gemma":[0.99884105,0.00019669814,0.00014600332,0.0006085427,0.000079705955,7.820292e-7,0.00010216612,0.000003292199,0.000021776854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9990771,0.0000868069,0.00014281727,0.0001419066,0.0004045964,0.00014679585],"domain_scores_gemma":[0.9995488,0.00022434855,0.000054506807,0.000113741124,0.000015907144,0.00004271482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033452123,0.000040919287,0.000083418156,0.0000033966062,0.0003510429,0.000012652559,0.00023501144,0.00001500708,0.00006973077],"category_scores_gemma":[0.00013132051,0.00004294415,0.000010523723,0.00025356907,0.00012905385,0.000027265081,0.00028054704,0.000106052044,2.7368478e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017690614,0.00037574273,0.032454062,0.000040683106,0.000049170183,0.0000066480784,0.087785564,0.0014884716,0.00004583968,0.5167577,0.009690659,0.35128772],"study_design_scores_gemma":[0.00027285362,0.00019846355,0.04503796,0.00004601165,0.000039862753,0.0000010397471,0.70978767,0.10496793,0.00017047467,0.03922942,0.09947706,0.0007712537],"about_ca_topic_score_codex":0.69885874,"about_ca_topic_score_gemma":0.51958555,"teacher_disagreement_score":0.6220021,"about_ca_system_score_codex":0.00042993156,"about_ca_system_score_gemma":0.0005583106,"threshold_uncertainty_score":0.48918074},"labels":[],"label_agreement":null},{"id":"W4313056002","doi":"10.1177/20539517221138767","title":"AI ethics and data governance in the geospatial domain of Digital Earth","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Innovation, Science and Economic Development Canada","keywords":"Geospatial analysis; Big data; Corporate governance; Digital Earth; Data science; Computer science; Political science; Engineering ethics; Sociology; Remote sensing; Engineering; Business; Data mining; Geography","score_opus":0.23927273513176184,"score_gpt":0.4135757287761156,"score_spread":0.17430299364435375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313056002","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47329107,0.0032024796,0.00054748234,0.4594852,0.0015806087,0.0011697777,0.042446684,0.00008178365,0.01819491],"genre_scores_gemma":[0.992113,0.0017209394,0.0002634648,0.0048775543,0.00031264874,0.0000033911774,0.0006016118,0.0000071809145,0.000100208716],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784374,0.00046688397,0.00017734905,0.00030701354,0.0009622403,0.0002427531],"domain_scores_gemma":[0.99795634,0.00089225464,0.00012193486,0.00092489424,0.00005490189,0.000049667513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007621591,0.0000733979,0.00012817349,0.0000052266214,0.0012172677,0.00025411902,0.0022118988,0.00011684977,0.00003192396],"category_scores_gemma":[0.0017143419,0.000062777166,0.000035297126,0.0002916139,0.00065603195,0.0008976907,0.0021704955,0.0011500284,0.0000010856638],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027163267,0.0003417112,0.010980447,0.000055892186,0.000075226926,0.000011381348,0.6319699,0.0000060505863,0.000037368773,0.14165854,0.19246008,0.022376224],"study_design_scores_gemma":[0.00035905838,0.00004662252,0.009798218,0.000012697278,0.00001393576,9.601565e-7,0.10196509,0.00017410805,9.882829e-7,0.020213028,0.8672566,0.00015868925],"about_ca_topic_score_codex":0.010575278,"about_ca_topic_score_gemma":0.019254921,"teacher_disagreement_score":0.6747965,"about_ca_system_score_codex":0.000034124936,"about_ca_system_score_gemma":0.0007139466,"threshold_uncertainty_score":0.99864113},"labels":[],"label_agreement":null},{"id":"W4313136413","doi":"10.1177/20539517221143361","title":"Cognitive assemblages: The entangled nature of algorithmic content moderation","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; International Centre for Comparative Criminology","funders":"Fondation du Risque; Institut Mines-Télécom","keywords":"Moderation; Computer science; Cognition; Limiting; Social media; Set (abstract data type); Data science; Computer security; Internet privacy; Cognitive science; World Wide Web; Psychology","score_opus":0.09870896551830664,"score_gpt":0.2820379095833584,"score_spread":0.18332894406505174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313136413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19373758,0.0010793104,0.79915273,0.0024880397,0.0018663087,0.00072894763,0.00044555851,0.00018591617,0.0003155861],"genre_scores_gemma":[0.99569494,0.000077823,0.0026651474,0.0009925506,0.00012867352,0.000038664035,0.0002841964,0.000006405206,0.00011159244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988073,0.00013522044,0.0001521348,0.0003357386,0.00041948215,0.00015011373],"domain_scores_gemma":[0.9989703,0.00009986244,0.00011514901,0.0006981581,0.0000879882,0.000028484817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006038033,0.00008595161,0.00009689393,0.000014114562,0.00045825006,0.00009315274,0.001103874,0.000054729368,0.000011617814],"category_scores_gemma":[0.00004029169,0.00006633159,0.00008131724,0.00030684142,0.000038683407,0.00033376328,0.0010040067,0.00038639506,0.0000049493733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009376435,0.00085005094,0.00035782834,0.00007842682,0.0007560946,0.00003299001,0.01950842,0.00030221816,0.06752566,0.00909389,0.1127334,0.78866726],"study_design_scores_gemma":[0.002377443,0.0006018588,0.0048420737,0.00006359399,0.00014735117,0.00014034289,0.02087559,0.86303437,0.059881784,0.0023749662,0.044893537,0.0007670923],"about_ca_topic_score_codex":0.0000943518,"about_ca_topic_score_gemma":0.000019322264,"teacher_disagreement_score":0.8627322,"about_ca_system_score_codex":0.000053371947,"about_ca_system_score_gemma":0.00009175259,"threshold_uncertainty_score":0.35245353},"labels":[],"label_agreement":null},{"id":"W4317910427","doi":"10.1177/20539517221149106","title":"Formally comparing topic models and human-generated qualitative coding of physician mothers’ experiences of workplace discrimination","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Human Genome Research Institute","keywords":"Coding (social sciences); Computer science; Thematic analysis; Leverage (statistics); Data science; Qualitative research; Topic model; Context (archaeology); Artificial intelligence; Sociology","score_opus":0.4102039748049899,"score_gpt":0.46940441320805104,"score_spread":0.05920043840306116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317910427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96686757,0.00008829956,0.03136003,0.00013075037,0.000066728884,0.00007635985,0.00002047775,0.000025222304,0.0013645682],"genre_scores_gemma":[0.99599874,0.000066809116,0.003507771,0.0000238673,0.000071779934,0.000005304631,0.00013390042,0.0000033032643,0.00018854969],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.999025,0.0002155369,0.0001984767,0.0001671289,0.00027862194,0.000115242794],"domain_scores_gemma":[0.99934274,0.00025687861,0.00015144367,0.00012778815,0.000093908544,0.000027246977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012719929,0.000057490324,0.00016800256,0.000029386163,0.00028857804,0.000029658824,0.00024063377,0.00003132535,0.000005024455],"category_scores_gemma":[0.00004887821,0.00005323977,0.000051592673,0.0005138638,0.00024347295,0.00035687845,0.00014416531,0.000039713235,3.9312334e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028998802,0.0000269436,0.00032336896,0.000034673216,0.000059526432,8.273729e-8,0.96126205,0.0006737225,0.0011289429,0.025117835,0.00057462306,0.010795343],"study_design_scores_gemma":[0.000161261,0.000013918696,0.0021257685,0.00004498506,0.000032235934,2.2855943e-8,0.87716764,0.11072488,0.0003798973,0.009074437,0.000178265,0.00009669325],"about_ca_topic_score_codex":0.00092214183,"about_ca_topic_score_gemma":0.00045961954,"teacher_disagreement_score":0.110051155,"about_ca_system_score_codex":0.000018505913,"about_ca_system_score_gemma":0.000045513647,"threshold_uncertainty_score":0.22195382},"labels":[],"label_agreement":null},{"id":"W4322580330","doi":"10.1177/20539517231158994","title":"The world wide web of carbon: Toward a relational footprinting of information and communications technology's climate impacts","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Green IT and Sustainability","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"Internet Society Foundation; Canada Research Chairs","keywords":"Carbon footprint; Information and Communications Technology; Big data; Climate change mitigation; Environmental economics; Greenhouse gas; Telecommunications; Environmental resource management; Computer science; Economics; World Wide Web","score_opus":0.05201531136187061,"score_gpt":0.2712900727471685,"score_spread":0.2192747613852979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322580330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959899,0.0005105663,0.00015466784,0.0017035835,0.00006307548,0.00016715995,0.00012261636,0.00017819725,0.0011102294],"genre_scores_gemma":[0.99753183,0.0010932417,0.0012173223,0.000005717741,0.000007821908,0.0000071921086,0.00012752989,0.000004642322,0.0000046904825],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999462,0.000012475871,0.00024683526,0.000053800763,0.00009269917,0.00013215735],"domain_scores_gemma":[0.99883765,0.00021965822,0.000067798916,0.0007881103,0.00006970552,0.000017097685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063190155,0.000053138694,0.000085182124,0.000044667184,0.00009853367,0.00001341737,0.00036496494,0.000051270003,4.093284e-7],"category_scores_gemma":[0.0002165756,0.000044655084,0.0000275107,0.0005657585,0.00017465114,0.00016474239,0.00064255384,0.00013850533,7.104598e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011464993,0.000024571711,0.89076537,0.0011863271,0.00023074167,2.3286407e-7,0.0058519477,0.0006150015,0.0013679368,0.016336057,0.0065788417,0.07703149],"study_design_scores_gemma":[0.00044900746,0.000016049931,0.6914006,0.0000926012,0.000044225344,0.0000015196063,0.0114515675,0.24383312,0.000435429,0.002208196,0.049886733,0.00018097946],"about_ca_topic_score_codex":0.000030101577,"about_ca_topic_score_gemma":0.00013762774,"teacher_disagreement_score":0.24321812,"about_ca_system_score_codex":0.000029299137,"about_ca_system_score_gemma":0.00005057422,"threshold_uncertainty_score":0.18209814},"labels":[],"label_agreement":null},{"id":"W4324277966","doi":"10.1177/20539517231163172","title":"All WARC and no playback: The materialities of data-centered web archives research","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Standardization; Metadata; World Wide Web; Interoperability; Data science","score_opus":0.4562295496170037,"score_gpt":0.3975399753386789,"score_spread":0.058689574278324774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324277966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8106482,0.002939621,0.027541906,0.044381578,0.003853623,0.0013516906,0.1021555,0.0014900283,0.0056378283],"genre_scores_gemma":[0.90701234,0.011909637,0.052084032,0.00095902855,0.0014337772,0.000027496046,0.022794995,0.00005144736,0.0037272403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806476,0.00025677372,0.00022927627,0.0006391259,0.00045265394,0.00035739207],"domain_scores_gemma":[0.995361,0.00051821064,0.00006787346,0.0039457437,0.00004435579,0.00006282981],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002478977,0.0001024515,0.00017545802,0.00004880204,0.0002489611,0.00037653063,0.005601711,0.000037522783,0.000008839025],"category_scores_gemma":[0.00015212811,0.00006937542,0.000042119987,0.00048166706,0.00041295143,0.0006961331,0.0114736585,0.00016195702,0.000074186435],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009645178,0.000042684052,0.0004703263,0.00010540389,0.00022233141,0.000003933638,0.0055872425,8.1581226e-7,0.0067376555,0.0011138166,0.96292835,0.02277779],"study_design_scores_gemma":[0.0005525509,0.000045768993,0.0039788894,0.000105090076,0.000051363142,0.0000070850874,0.0044814176,0.24699251,0.00038817813,0.00080127,0.74233574,0.00026014613],"about_ca_topic_score_codex":0.00033216906,"about_ca_topic_score_gemma":0.000040988838,"teacher_disagreement_score":0.2469917,"about_ca_system_score_codex":0.000005659326,"about_ca_system_score_gemma":0.00012038806,"threshold_uncertainty_score":0.99977845},"labels":[],"label_agreement":null},{"id":"W4328024595","doi":"10.1177/20539517231164118","title":"Fact signalling and fact nostalgia in the data-driven society","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Performative utterance; Legitimacy; Aesthetics; Sociology; Narrative; Normative; Public sphere; Epistemology; Solidarity; Law and economics; Law; Political science; Politics; Philosophy","score_opus":0.3134276309657378,"score_gpt":0.3899554568788797,"score_spread":0.07652782591314194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328024595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95544267,0.00053819764,0.0023384108,0.021290472,0.00082558946,0.001367117,0.005987002,0.00056685874,0.011643685],"genre_scores_gemma":[0.98925054,0.0041519506,0.0005680144,0.0023460214,0.00033197788,0.0000019077581,0.0030334021,0.000011162494,0.00030503827],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983811,0.0001248324,0.00022266556,0.0003005755,0.00056859537,0.0004022813],"domain_scores_gemma":[0.9986351,0.0003390458,0.00008948346,0.0008050811,0.000029459747,0.00010184294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029306188,0.00011470237,0.00013093317,0.000016745678,0.0007070681,0.00039446287,0.0015219289,0.000116936775,0.00007418747],"category_scores_gemma":[0.00031458013,0.000084317224,0.00006173989,0.0006251688,0.00022498594,0.0013480948,0.0007123069,0.00023962051,0.00010472504],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002354698,0.000025157837,0.0013496146,0.00003121759,0.0000396027,0.000001496061,0.2663011,0.000021562386,0.000112671274,0.00033856288,0.70811355,0.023663135],"study_design_scores_gemma":[0.00053806807,0.000017797549,0.04557497,0.000041738742,0.00002909141,0.0000013922227,0.31224045,0.031143699,0.000010955613,0.0002048567,0.60987926,0.00031768737],"about_ca_topic_score_codex":0.001339216,"about_ca_topic_score_gemma":0.0008956859,"teacher_disagreement_score":0.09823426,"about_ca_system_score_codex":0.000045713758,"about_ca_system_score_gemma":0.00024619704,"threshold_uncertainty_score":0.54382676},"labels":[],"label_agreement":null},{"id":"W4366122282","doi":"10.1177/20539517231163174","title":"Recording the ethical provenance of data and automating data stewardship","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; European Commission","keywords":"Stewardship (theology); Interoperability; Data governance; Compromise; Normative; Data science; Data exchange; Computer science; Scale (ratio); Knowledge management; Business; Political science; Data quality; Law; World Wide Web","score_opus":0.8288543813695006,"score_gpt":0.606879055657871,"score_spread":0.2219753257116296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366122282","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37721705,0.0049836454,0.0061762515,0.5641377,0.0021523642,0.0040225503,0.03664768,0.0011547556,0.0035080046],"genre_scores_gemma":[0.9168863,0.015388745,0.0460658,0.0048251967,0.0016982002,0.000018687273,0.013959672,0.000085160864,0.001072209],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996647,0.00021837055,0.0005380385,0.0010027601,0.0012195389,0.0003743111],"domain_scores_gemma":[0.968792,0.019774554,0.00020645407,0.010859704,0.00020676236,0.00016051321],"candidate_categories":["metaresearch","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028728567,0.000118022486,0.00031190264,0.000016452686,0.00023014966,0.00006576233,0.0041309088,0.00047370358,0.000015117169],"category_scores_gemma":[0.06257855,0.00007863441,0.000039269693,0.00056270184,0.00072982284,0.0003061519,0.018931432,0.0033910729,0.000024049812],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008879543,0.00015422644,0.014592921,0.0037864957,0.00044063234,0.00004795609,0.0021954642,7.426586e-7,0.002583247,0.0024972032,0.6460282,0.32758412],"study_design_scores_gemma":[0.003410675,0.0003881865,0.07337917,0.004658012,0.00052338216,0.00006557764,0.011732486,0.62583464,0.00032099243,0.019831825,0.25921404,0.00064104266],"about_ca_topic_score_codex":0.00023233169,"about_ca_topic_score_gemma":0.00016839975,"teacher_disagreement_score":0.62583387,"about_ca_system_score_codex":0.000024428418,"about_ca_system_score_gemma":0.00077153253,"threshold_uncertainty_score":0.99890816},"labels":[],"label_agreement":null},{"id":"W4378231474","doi":"10.1177/20539517231177621","title":"Surveillance capitalism and systemic digital risk: The imperative to collect and connect and the risks of interconnectedness","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Capitalism; Sociology; Dystopia; Capitalist system; Neoclassical economics; Business; Economics; Political science; Politics; Law","score_opus":0.057333900144999644,"score_gpt":0.2874171441310782,"score_spread":0.23008324398607857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378231474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9812365,0.001508866,0.012789936,0.003211115,0.00007272053,0.0004626805,0.0006016915,0.00009856369,0.000017926877],"genre_scores_gemma":[0.9981604,0.0014001222,0.0002167728,0.00011174807,0.000021416015,0.000048846607,0.000020955655,0.0000045427623,0.000015182601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991017,0.00010605222,0.00016287858,0.00039027663,0.00009407564,0.00014504766],"domain_scores_gemma":[0.9979653,0.00090689224,0.00009074785,0.0009391131,0.00006265663,0.00003530265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010319182,0.00010163301,0.00018854131,0.00001966474,0.00036958998,0.00017620475,0.00085881475,0.000070781054,2.7327272e-7],"category_scores_gemma":[0.00024435626,0.0000581341,0.000025111718,0.0005359796,0.00056341005,0.00012992405,0.0017912822,0.00015520061,0.0000016588765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001118423,0.00015851528,0.05803931,0.0003614231,0.0011789574,0.000009428842,0.22966985,0.000025072577,0.001453392,0.34185043,0.09051023,0.27663153],"study_design_scores_gemma":[0.008190158,0.00047118994,0.26589626,0.0002641351,0.00015300709,0.0005321419,0.06482707,0.5957503,0.001092333,0.04502276,0.016180541,0.0016201537],"about_ca_topic_score_codex":0.00031137923,"about_ca_topic_score_gemma":0.00015881569,"teacher_disagreement_score":0.5957252,"about_ca_system_score_codex":0.000009192418,"about_ca_system_score_gemma":0.000031657313,"threshold_uncertainty_score":0.28426245},"labels":[],"label_agreement":null},{"id":"W4381856247","doi":"10.1177/20539517231182402","title":"Data infrastructure studies on an unequal planet","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Digital Economy and Work Transformation","field":"Social Sciences","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de Recherche du Québec-Société et Culture; University College Dublin","keywords":"Capitalism; Multinational corporation; Externality; Big data; Environmental data; Data science; Function (biology); Supply chain; Politics; Computer science; Business; Economics; Political science","score_opus":0.23201467672185852,"score_gpt":0.377332185539475,"score_spread":0.1453175088176165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381856247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7787859,0.0008864701,0.0004971178,0.01731577,0.010221913,0.001681747,0.11512338,0.0026657868,0.07282191],"genre_scores_gemma":[0.9217915,0.0024577603,0.000368971,0.0013782375,0.0014762959,0.000006646777,0.072102174,0.000014938591,0.0004034807],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898666,0.000056948324,0.00016518263,0.00031854573,0.00023558148,0.0002370686],"domain_scores_gemma":[0.99887663,0.00012877923,0.00005326654,0.0008474934,0.000017881724,0.00007594935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010939208,0.00008776214,0.0001121779,0.000015113546,0.00047792756,0.00016437219,0.0011865814,0.00008388307,0.000026049382],"category_scores_gemma":[0.00010518762,0.00007849015,0.000017950028,0.00027248135,0.00019170374,0.0017343678,0.0003349941,0.000115076036,0.00021152735],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006858889,0.000028611372,0.00037606576,0.000024300334,0.00008883687,0.0000018249184,0.029754547,0.00014204448,0.0000018813316,0.00665493,0.83427584,0.12864423],"study_design_scores_gemma":[0.00013304171,0.00002098721,0.0009517035,0.000012677036,0.000012120027,1.3455579e-7,0.054912858,0.001125243,0.0000020658317,0.0011978911,0.9415065,0.00012477538],"about_ca_topic_score_codex":0.00017220779,"about_ca_topic_score_gemma":0.003014682,"teacher_disagreement_score":0.14300558,"about_ca_system_score_codex":0.000035536767,"about_ca_system_score_gemma":0.0001266555,"threshold_uncertainty_score":0.36758807},"labels":[],"label_agreement":null},{"id":"W4382355891","doi":"10.1177/20539517231171053","title":"Prediction as extraction of discretion","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Discretion; Officer; Predictive power; Productivity; Redistribution (election); Power (physics); Focus (optics); Work (physics); Sociology; Computer science; Economics; Law; Political science; Epistemology; Engineering; Politics","score_opus":0.3282374062916354,"score_gpt":0.44560957319635897,"score_spread":0.11737216690472357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382355891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8452883,0.00038339247,0.006824624,0.049165998,0.0073171784,0.0010319537,0.0025021203,0.0012800469,0.08620641],"genre_scores_gemma":[0.9921743,0.0042095957,0.0001861171,0.0001973971,0.00088209985,0.0000037911345,0.00061208283,0.000008987341,0.00172558],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888223,0.00009458661,0.00014985047,0.00018482965,0.0004947431,0.00019373564],"domain_scores_gemma":[0.9992352,0.00015228173,0.0000994367,0.00030181522,0.00013571202,0.000075530064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020414586,0.000054100095,0.00008552229,0.000018271674,0.000542943,0.00007636646,0.00030230056,0.00019156437,0.00006136184],"category_scores_gemma":[0.0006777297,0.00005487517,0.00007445949,0.0004517568,0.000258366,0.0007493793,0.000087633896,0.00016770883,0.00006367036],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003599929,0.00026680971,0.0048728003,0.00012519318,0.00022004671,0.0000040269533,0.20766814,0.000031303316,0.012025672,0.045517452,0.5847131,0.14451946],"study_design_scores_gemma":[0.0005465061,0.00012600234,0.05762611,0.000101584876,0.000105808846,8.83514e-7,0.13639387,0.0019707005,0.0005087304,0.037043884,0.76523,0.0003459164],"about_ca_topic_score_codex":0.0062992126,"about_ca_topic_score_gemma":0.0012092293,"teacher_disagreement_score":0.18051691,"about_ca_system_score_codex":0.000060820625,"about_ca_system_score_gemma":0.000246062,"threshold_uncertainty_score":0.9522567},"labels":[],"label_agreement":null},{"id":"W4382402873","doi":"10.1177/20539517231184891","title":"Clicks and particulates: Value, alienation, and attunement as unifying themes in big data studies","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Race, Genetics, and Society","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fulbright Association","keywords":"Attunement; Alienation; Value (mathematics); Appropriation; Sociology; Capitalism; Epistemology; Political science; Politics; Law; Computer science","score_opus":0.19113664776621064,"score_gpt":0.3666263066005908,"score_spread":0.17548965883438017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382402873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9840326,0.013376475,0.000119318844,0.0014618518,0.0002767072,0.0002212875,0.00041586172,0.000026943131,0.00006900823],"genre_scores_gemma":[0.8889712,0.10557614,0.00076180464,0.0009733553,0.0004647952,0.000015039828,0.002906283,0.000023608729,0.00030775904],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984914,0.000061603096,0.00025071535,0.00074015156,0.00017083767,0.00028528462],"domain_scores_gemma":[0.99856037,0.000047550748,0.00006999261,0.0011954391,0.000056821118,0.00006984617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008518563,0.0001639638,0.00017589085,0.000014803325,0.00021805304,0.00005963432,0.00043159,0.00013186528,0.0000013800715],"category_scores_gemma":[0.00021762142,0.00014741304,0.000035957542,0.00016942326,0.0002644512,0.000014736717,0.00236271,0.00008669539,0.000004191923],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006817479,0.00035556988,0.12257453,0.00073987583,0.002230451,0.000018924851,0.030897975,0.0002164668,0.12665123,0.00032916619,0.6026371,0.113280505],"study_design_scores_gemma":[0.0042361366,0.0002986109,0.12239423,0.00019224346,0.00032394347,0.000020870648,0.099352,0.0124833,0.013190544,0.0014790295,0.7446077,0.001421387],"about_ca_topic_score_codex":0.00007093272,"about_ca_topic_score_gemma":0.00017786935,"teacher_disagreement_score":0.14197057,"about_ca_system_score_codex":0.000013518936,"about_ca_system_score_gemma":0.000072048286,"threshold_uncertainty_score":0.6011329},"labels":[],"label_agreement":null},{"id":"W4384830785","doi":"10.1177/20539517231188724","title":"Cities, COVID-19, and counting","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Pandemic; Data science; Data collection; Coronavirus disease 2019 (COVID-19); Big data; Scale (ratio); Consistency (knowledge bases); Rigour; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Political science; Regional science; Geography; Sociology; Computer science; Cartography; Social science; Data mining","score_opus":0.6924434970998441,"score_gpt":0.4825174488772752,"score_spread":0.20992604822256888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384830785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75988334,0.009121024,0.07299466,0.13077785,0.0024161404,0.0027509134,0.009251503,0.008118677,0.0046858974],"genre_scores_gemma":[0.7713149,0.028824667,0.069810554,0.11504963,0.0044670086,0.00027121042,0.0033345588,0.00023717614,0.0066902656],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858665,0.00007900635,0.00028051835,0.0004768918,0.00021957514,0.00035737813],"domain_scores_gemma":[0.99360895,0.0054053543,0.00010914296,0.0007198473,0.000027869635,0.00012881368],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024980244,0.000149916,0.00030814705,0.000013328053,0.0004439463,0.00004468302,0.00044018537,0.00010609507,0.000040938576],"category_scores_gemma":[0.015089549,0.00011885702,0.000072159695,0.00030334314,0.0002335062,0.00009994773,0.002020299,0.00016475806,0.00004861734],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025231786,0.0000145752365,0.0127661815,0.00037699056,0.00007384116,0.000005584829,0.0013174034,0.0000013252018,0.00003467194,0.0041734125,0.9787017,0.0025317606],"study_design_scores_gemma":[0.00038434964,0.000016384913,0.009073961,0.000026433847,0.00005580785,0.000003223011,0.0030189634,0.0026503683,0.0000034382738,0.08752638,0.8969861,0.000254537],"about_ca_topic_score_codex":0.00038543294,"about_ca_topic_score_gemma":0.00014331903,"teacher_disagreement_score":0.08335297,"about_ca_system_score_codex":0.0001038176,"about_ca_system_score_gemma":0.000092638336,"threshold_uncertainty_score":0.9932068},"labels":[],"label_agreement":null},{"id":"W4390117685","doi":"10.1177/20539517231219242","title":"Freezing out: Legacy media's shaping of AI as a cold controversy","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University; Institut National de la Recherche Scientifique","funders":"","keywords":"Mainstream; Newspaper; Big data; Cold war; Political science; Sociology; Public relations; Media studies; Artificial intelligence; Politics; Computer science; Law","score_opus":0.318867288523025,"score_gpt":0.43123871608173164,"score_spread":0.11237142755870666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390117685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51344025,0.0030593683,0.0012221565,0.3275446,0.013966414,0.0024291344,0.0046270844,0.0020399876,0.13167098],"genre_scores_gemma":[0.9904571,0.001994187,0.00020406491,0.004829275,0.0015256372,0.0000051536417,0.00018604657,0.000022223287,0.00077628053],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790496,0.00014005367,0.00027073993,0.00033072525,0.00083872926,0.0005147759],"domain_scores_gemma":[0.99784636,0.0009843012,0.00015357474,0.0005452628,0.000268021,0.00020247506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032821773,0.00012203343,0.00027334967,0.000029422314,0.0008077026,0.00033191952,0.0010351998,0.00027489543,0.000059170354],"category_scores_gemma":[0.004482249,0.00012683391,0.00017439987,0.0005372214,0.00062075414,0.0011564184,0.00051645515,0.00041889536,0.00010409575],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012134315,0.000082251405,0.0011103214,0.00007163022,0.00023225845,0.000012422324,0.2554762,0.0000031276736,0.0042307936,0.13732506,0.5939183,0.007525434],"study_design_scores_gemma":[0.001129308,0.00005224037,0.0015606731,0.0001657845,0.00009855364,2.4223664e-7,0.1493757,0.00040681215,0.0004872765,0.020330703,0.8259156,0.00047714968],"about_ca_topic_score_codex":0.014155912,"about_ca_topic_score_gemma":0.009177673,"teacher_disagreement_score":0.47701687,"about_ca_system_score_codex":0.00009423177,"about_ca_system_score_gemma":0.00092808437,"threshold_uncertainty_score":0.99240893},"labels":[],"label_agreement":null},{"id":"W4390760903","doi":"10.1177/20539517231224247","title":"A feeling for the algorithm: Diversity, expertise, and artificial intelligence","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council","keywords":"Diversity (politics); Sociology; Epistemology; Normative; Set (abstract data type); Computer science; CLARITY; Feeling; Artificial intelligence; Social psychology; Psychology","score_opus":0.4130394589546723,"score_gpt":0.43367751830361756,"score_spread":0.020638059348945248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390760903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013056321,0.031963106,0.69626325,0.23864868,0.011713288,0.002027107,0.0022125668,0.0006589633,0.0034566794],"genre_scores_gemma":[0.9647267,0.018558675,0.008109118,0.0026732641,0.005231896,0.000018864339,0.00007931225,0.000023639399,0.00057854847],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989789,0.000045769044,0.00011438206,0.000281583,0.00031434296,0.00026503904],"domain_scores_gemma":[0.99872607,0.0008206104,0.000024311656,0.00024609917,0.00009405127,0.00008882952],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0020443795,0.000077569566,0.00008606815,0.0000090402855,0.0027216268,0.0007687859,0.00065098243,0.00013103896,0.000014977652],"category_scores_gemma":[0.0004797392,0.000059227907,0.00008664901,0.00019233514,0.00053771114,0.00046095325,0.00092305645,0.00020573275,0.0000073476676],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002382736,0.000015845064,0.000019169522,0.000020434212,0.00006853057,0.0000013524931,0.13039492,9.3073334e-7,0.000021884505,0.033925753,0.033032652,0.80249614],"study_design_scores_gemma":[0.00007236439,0.000050041876,0.00014179393,0.00009602516,0.00016758377,7.7954473e-7,0.18697174,0.059002105,0.000065964196,0.15581901,0.5972165,0.00039613247],"about_ca_topic_score_codex":0.0043656323,"about_ca_topic_score_gemma":0.0022275944,"teacher_disagreement_score":0.95167035,"about_ca_system_score_codex":0.000056385812,"about_ca_system_score_gemma":0.00021458445,"threshold_uncertainty_score":0.9985767},"labels":[],"label_agreement":null},{"id":"W4392004153","doi":"10.1177/20539517241231270","title":"Super SDKs: Tracking personal data and platform monopolies in the mobile","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Tracking (education); Computer science; Computer security; Internet privacy; Data science; Sociology","score_opus":0.19090046531329874,"score_gpt":0.36746582965167124,"score_spread":0.1765653643383725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392004153","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9309448,0.036343392,0.0015034481,0.010091916,0.002673513,0.0015553844,0.011953967,0.00036931955,0.004564239],"genre_scores_gemma":[0.9896998,0.006610914,0.00030898178,0.0003973567,0.001228808,0.000025356825,0.0016505942,0.000010160762,0.00006805502],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986437,0.00008545239,0.0001425709,0.00048399123,0.00036266763,0.0002816297],"domain_scores_gemma":[0.99870795,0.00025241144,0.000021674086,0.0009537252,0.000015407659,0.000048818212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024624271,0.000101244776,0.00009965749,0.000021220798,0.0005913728,0.0006658439,0.0018275157,0.0001119517,0.00006197093],"category_scores_gemma":[0.0003026231,0.00007558184,0.000033326593,0.00030452933,0.0003322704,0.0021293997,0.0014304944,0.00031496165,0.000021116],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008984157,0.00010140035,0.0021389553,0.00014229497,0.00006220387,0.000013642067,0.35132983,2.229615e-7,0.0001384756,0.0029211706,0.44108617,0.20205665],"study_design_scores_gemma":[0.00012983302,0.000015517502,0.0015316854,0.00004299416,0.000026461035,0.000009597411,0.14840566,0.004896716,0.00000649436,0.0017649706,0.84301823,0.00015184774],"about_ca_topic_score_codex":0.006838613,"about_ca_topic_score_gemma":0.007644914,"teacher_disagreement_score":0.40193206,"about_ca_system_score_codex":0.000059334754,"about_ca_system_score_gemma":0.00019105384,"threshold_uncertainty_score":0.99977493},"labels":[],"label_agreement":null},{"id":"W4392165174","doi":"10.1177/20539517241227875","title":"Critical data studies with Latin America: Theorizing beyond data colonialism","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Colonialism; Latin Americans; Sociology; Political science; History; Law","score_opus":0.42149704920330266,"score_gpt":0.4939632852374883,"score_spread":0.07246623603418562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392165174","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01758742,0.07265022,0.008046114,0.7607343,0.013732222,0.001979514,0.07589198,0.0021921087,0.047186103],"genre_scores_gemma":[0.887358,0.040799487,0.031220416,0.014136143,0.01194792,0.000020152076,0.012590181,0.00013863828,0.0017890792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967977,0.00033063555,0.00027107543,0.0010803941,0.0009112776,0.00060891034],"domain_scores_gemma":[0.99342436,0.0028717876,0.00006617809,0.003149966,0.00027032036,0.000217414],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0048738667,0.00020526882,0.00033286787,0.000019643661,0.0015867295,0.0012985943,0.0041944417,0.00022747606,0.00004603552],"category_scores_gemma":[0.0069458224,0.00016353258,0.000047767713,0.0006092192,0.0027851465,0.0030500125,0.0048986585,0.0007266843,0.00005036641],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000098396085,0.000075315744,0.00012277658,0.00012995592,0.0005087629,0.000042333566,0.077615865,3.0556436e-7,0.000037411894,0.098236285,0.7969177,0.026303463],"study_design_scores_gemma":[0.00013691104,0.000047937374,0.000114251525,0.00016340602,0.00023561151,0.0000013793809,0.07799295,0.0010088155,0.0000019898368,0.014376989,0.9055973,0.0003223998],"about_ca_topic_score_codex":0.004254326,"about_ca_topic_score_gemma":0.006211113,"teacher_disagreement_score":0.8697706,"about_ca_system_score_codex":0.000103568236,"about_ca_system_score_gemma":0.0012085093,"threshold_uncertainty_score":0.9999287},"labels":[],"label_agreement":null},{"id":"W4392167202","doi":"10.1177/20539517241234279","title":"Harvesting value: Corporate strategies of data assetization in agriculture and their socio-ecological implications","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Agriculture, Land Use, Rural Development","field":"Agricultural and Biological Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Bundesministerium für Bildung und Forschung","keywords":"Value (mathematics); Agriculture; Ecology; Sociology; Environmental resource management; Economics; Geography; Natural resource economics; Mathematics; Biology; Statistics","score_opus":0.182212719071677,"score_gpt":0.2873631351853523,"score_spread":0.10515041611367529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392167202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99234307,0.0014801249,0.00019259892,0.0020891596,0.00012543074,0.00032163653,0.003118747,0.00012432998,0.00020489216],"genre_scores_gemma":[0.9824191,0.0010979302,0.00115304,0.00010768673,0.00024597615,0.000014238639,0.014870593,0.0000013854519,0.00009009849],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986504,0.000075594035,0.00030579424,0.00060667197,0.0001391667,0.00022242626],"domain_scores_gemma":[0.999276,0.00025988018,0.00013544143,0.0002069156,0.000059754184,0.00006205486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052810187,0.00017497085,0.00019826516,0.0000053493745,0.00017504727,0.00023969344,0.0007931332,0.00017826611,0.000017863478],"category_scores_gemma":[0.000054001444,0.000054380012,0.00004058855,0.00061038544,0.00009575363,0.0007844168,0.00089487655,0.00019686528,0.000004906904],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016301328,0.0006356011,0.08746002,0.0003802132,0.00032246474,0.000012025561,0.0032967522,0.000069025176,0.15191048,0.042718437,0.29134384,0.42183483],"study_design_scores_gemma":[0.00008554089,0.00003935024,0.96063906,0.00008142435,0.000022328672,0.00001123333,0.00596585,0.0010436393,0.000120333316,0.009054487,0.022715125,0.00022163733],"about_ca_topic_score_codex":0.0002160077,"about_ca_topic_score_gemma":0.00082577154,"teacher_disagreement_score":0.873179,"about_ca_system_score_codex":0.00003497632,"about_ca_system_score_gemma":0.000050227067,"threshold_uncertainty_score":0.23113695},"labels":[],"label_agreement":null},{"id":"W4396560109","doi":"10.1177/20539517241242446","title":"Deeply embedded wages: Navigating digital payments in data work","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Digital Economy and Work Transformation","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Payment; Work (physics); Labour economics; Computer science; Internet privacy; Economics; Sociology; Data science; Computer security; World Wide Web; Engineering","score_opus":0.11760151751597675,"score_gpt":0.3463064806024165,"score_spread":0.22870496308643973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396560109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6993703,0.010452863,0.010819833,0.021384595,0.009906924,0.0027242703,0.011776548,0.0021093788,0.23145527],"genre_scores_gemma":[0.99171805,0.0005296706,0.00053663837,0.00028649755,0.0005171972,0.000007984331,0.006064977,0.000013807691,0.00032516467],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986284,0.000032883614,0.0002844048,0.00045048833,0.0002661516,0.00033771168],"domain_scores_gemma":[0.9989881,0.0001572301,0.000038762464,0.0007169925,0.000013873902,0.0000850565],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009919959,0.000110569665,0.00011936585,0.000013085474,0.00023106967,0.0016384578,0.0012234303,0.00009456671,0.000030508596],"category_scores_gemma":[0.00010809341,0.000108697575,0.00005291587,0.000592436,0.0001494606,0.0071305605,0.0004591147,0.00024303548,0.00020227692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003421713,0.00005060395,0.0022992566,0.000044974746,0.000043696742,0.000005484643,0.023177454,0.000003132371,8.604694e-7,0.000641276,0.049637485,0.92409235],"study_design_scores_gemma":[0.00022396968,0.0000075318476,0.0005825783,0.000495348,0.000017681516,6.916027e-7,0.025022436,0.002203119,0.0000041859007,0.0012807436,0.9698776,0.00028411328],"about_ca_topic_score_codex":0.00017935137,"about_ca_topic_score_gemma":0.000438462,"teacher_disagreement_score":0.9238082,"about_ca_system_score_codex":0.0000963725,"about_ca_system_score_gemma":0.00020099456,"threshold_uncertainty_score":0.99939793},"labels":[],"label_agreement":null},{"id":"W4401642149","doi":"10.1177/20539517241274593","title":"Interoperable and standardized algorithmic images: The domestic war on drugs and mugshots within facial recognition technologies","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Global Security and Public Health","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Interoperability; Facial recognition system; Data science; Artificial intelligence; Pattern recognition (psychology); World Wide Web","score_opus":0.07127892179494628,"score_gpt":0.34950392334290836,"score_spread":0.2782250015479621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401642149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76897395,0.03614199,0.0025956586,0.14888859,0.005870693,0.0033389993,0.014761108,0.003152028,0.01627701],"genre_scores_gemma":[0.97582906,0.021408936,0.0010035817,0.0009628448,0.0003835778,0.000024664048,0.00022150014,0.000012771551,0.00015304687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99868685,0.00016995969,0.00015826832,0.00038651554,0.00031222677,0.00028616458],"domain_scores_gemma":[0.9993259,0.00024645147,0.000035950226,0.00027334059,0.00004681907,0.00007154736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021831244,0.0001132841,0.00013753223,0.000021463062,0.0008282734,0.0004261804,0.0003640955,0.00015265458,0.000021469428],"category_scores_gemma":[0.00046609246,0.00007641455,0.000034229848,0.00030664288,0.0006970398,0.00041118325,0.0002800646,0.0003604461,0.00001935873],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017975824,0.000027553524,0.000022223418,0.000100881254,0.000053586085,0.0000073217634,0.056660984,1.7462072e-7,0.00003079321,0.0012628705,0.08235737,0.85945827],"study_design_scores_gemma":[0.00044138197,0.000099084,0.00010979416,0.00023407266,0.00004437875,0.000008489126,0.12663859,0.0008227528,0.000045004203,0.010586544,0.8607365,0.00023340149],"about_ca_topic_score_codex":0.0035708789,"about_ca_topic_score_gemma":0.00078814564,"teacher_disagreement_score":0.85922486,"about_ca_system_score_codex":0.00009707839,"about_ca_system_score_gemma":0.00029132527,"threshold_uncertainty_score":0.6370493},"labels":[],"label_agreement":null},{"id":"W4403431383","doi":"10.1177/20539517241290220","title":"From human-centered to social-centered artificial intelligence: Assessing ChatGPT's impact through disruptive events","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Sociology; Computer science; Data science; Psychology","score_opus":0.45097043780696217,"score_gpt":0.5262443725385693,"score_spread":0.0752739347316071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403431383","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8742669,0.0017454223,0.028182914,0.062196158,0.009155937,0.0017162809,0.011694658,0.0010520117,0.009989668],"genre_scores_gemma":[0.98929334,0.0004983725,0.0010350533,0.0012991356,0.0063101696,0.000013958778,0.0012507602,0.00006025754,0.00023897555],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9959783,0.00040450323,0.000569427,0.000981435,0.0011140598,0.00095226814],"domain_scores_gemma":[0.9981859,0.00037884957,0.000163269,0.0006791425,0.0002496689,0.0003431866],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00206823,0.0003557088,0.00044091803,0.000045545927,0.0024580355,0.0023386667,0.0015096929,0.00048936537,0.00030903632],"category_scores_gemma":[0.0005706361,0.00033821244,0.00049515266,0.0008365533,0.0005174744,0.0025266774,0.00084171054,0.0007757736,0.00021141759],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003556812,0.00053788075,0.00044720923,0.00006893901,0.00091021415,0.000033070744,0.7428713,0.0000034284913,0.0030098679,0.021525221,0.11291105,0.117646255],"study_design_scores_gemma":[0.000459337,0.00023791636,0.008676182,0.0010975103,0.00047372625,0.0000015478902,0.4124779,0.0008185924,0.000617396,0.36001816,0.21293354,0.0021881883],"about_ca_topic_score_codex":0.023250781,"about_ca_topic_score_gemma":0.00408678,"teacher_disagreement_score":0.33849293,"about_ca_system_score_codex":0.0007258644,"about_ca_system_score_gemma":0.0008744926,"threshold_uncertainty_score":0.999907},"labels":[],"label_agreement":null},{"id":"W4404050091","doi":"10.1177/20539517241289443","title":"Artificial intelligence as planetary assemblages of coloniality: The new power architecture driving a tiered global data economy","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Digital Economy and Work Transformation","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Architecture; Power (physics); Computer science; Data science; Economy; History; Economics","score_opus":0.10095605799414412,"score_gpt":0.33737010924499683,"score_spread":0.2364140512508527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404050091","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18471281,0.009947469,0.22545189,0.15923168,0.009087548,0.003755924,0.017506389,0.0011218397,0.38918447],"genre_scores_gemma":[0.99655175,0.00025944374,0.00048733747,0.0004823481,0.00058889075,0.0000025924462,0.0014934546,0.0000065485906,0.00012762996],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987432,0.00008100954,0.0003197379,0.0003803684,0.0001989386,0.00027675732],"domain_scores_gemma":[0.998719,0.00026388644,0.00007255823,0.00082659296,0.000018579076,0.000099429526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012588237,0.000116762516,0.00014920406,0.00001133708,0.00027558632,0.000533799,0.001690882,0.000110954556,0.0001351617],"category_scores_gemma":[0.00011228131,0.00009330221,0.00007796839,0.00030595498,0.00031598142,0.0011816376,0.00040225702,0.00017856628,0.00009933065],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019494986,0.00005311307,0.00038822123,0.00006224818,0.00023869789,0.0000037752543,0.020118395,0.00004827043,0.000005465251,0.0606558,0.11710785,0.8012987],"study_design_scores_gemma":[0.00002639653,0.000026281787,0.0002921976,0.00007373913,0.000054797056,0.000003593983,0.0077955863,0.0015441221,0.000028485827,0.046315808,0.9436689,0.00017006489],"about_ca_topic_score_codex":0.0021464028,"about_ca_topic_score_gemma":0.00744105,"teacher_disagreement_score":0.8265611,"about_ca_system_score_codex":0.00006411664,"about_ca_system_score_gemma":0.0009050235,"threshold_uncertainty_score":0.51474357},"labels":[],"label_agreement":null},{"id":"W4405616447","doi":"10.1177/20539517241299732","title":"The emergence of artificial intelligence ethics auditing","year":2024,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Audit; Engineering ethics; Sociology; Information ethics; Computer science; Epistemology; Artificial intelligence; Political science; Data science; Engineering; Business; Philosophy; Accounting","score_opus":0.4928326761661721,"score_gpt":0.48793115814855514,"score_spread":0.004901518017616957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405616447","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039037317,0.03581667,0.111970775,0.6663133,0.036366303,0.0018436052,0.0024202268,0.0013189777,0.10491286],"genre_scores_gemma":[0.9767729,0.01913229,0.0009790729,0.0006360672,0.0020343347,0.0000036451572,0.000033932665,0.000014532305,0.00039322328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981051,0.0002351699,0.0003046642,0.00027490372,0.00073346647,0.00034669167],"domain_scores_gemma":[0.9967174,0.002343405,0.00009109303,0.00048528938,0.00027291055,0.00008991917],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00844818,0.000086399195,0.000107337495,0.000009279268,0.0019237795,0.00044007832,0.0011910971,0.0002542457,0.000058033896],"category_scores_gemma":[0.0053712516,0.00006647568,0.00012664722,0.0005221763,0.0012693731,0.00042138252,0.00036873214,0.00084888184,0.000034108703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021796131,0.000021830609,0.000023359367,0.000059432212,0.0000654854,0.0000017534979,0.14055888,0.0000038995195,0.00027717755,0.56586653,0.055003155,0.23811632],"study_design_scores_gemma":[0.000014165973,0.000027894284,0.00009085571,0.00017296555,0.000051279123,3.6208797e-7,0.20239006,0.0035042241,0.0003671076,0.20273103,0.5903918,0.00025824187],"about_ca_topic_score_codex":0.0035469588,"about_ca_topic_score_gemma":0.0067590773,"teacher_disagreement_score":0.93773556,"about_ca_system_score_codex":0.000035006648,"about_ca_system_score_gemma":0.0011652854,"threshold_uncertainty_score":0.9993756},"labels":[],"label_agreement":null},{"id":"W4407049658","doi":"10.1177/20539517241311584","title":"Undermining competition, undermining markets? Implications of Big Tech and digital personal data for competition policy","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"ICT Impact and Policies","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Competition (biology); Market power; Order (exchange); Underpinning; Economics; Big data; Policy analysis; Public policy; Competition law; Digital economy; Politics; Business; Industrial organization; Public economics; Market economy; Political science; Economic growth; Public administration; Finance","score_opus":0.08561016010257505,"score_gpt":0.3180196689325161,"score_spread":0.23240950882994105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407049658","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3776769,0.0027033528,0.47506353,0.009353165,0.0011618675,0.0013896951,0.10177511,0.0010004252,0.029875953],"genre_scores_gemma":[0.9886293,0.00038190375,0.0012029804,0.00023096037,0.0003342728,0.000012181882,0.009075952,0.000022977416,0.00010949195],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992541,0.000009403078,0.00023390783,0.00017091414,0.00009172425,0.0002399413],"domain_scores_gemma":[0.9988235,0.0002511776,0.00004963878,0.0007733115,0.000048907867,0.000053466592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018355165,0.00014456677,0.00018372535,0.00007206972,0.00018876299,0.00012161152,0.0004922441,0.000087545544,0.0000049133587],"category_scores_gemma":[0.00009804905,0.00015559825,0.000046351866,0.00031111573,0.00013880544,0.00038821922,0.00044786194,0.000105600346,0.0000014209794],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058449325,0.00035681756,0.016071476,0.0042381035,0.0016847996,7.281967e-7,0.015610257,0.00018138441,0.011884924,0.15229304,0.39389393,0.4037261],"study_design_scores_gemma":[0.0037162555,0.00011935721,0.17964578,0.0011511707,0.0004898694,0.00007761014,0.03233207,0.1343502,0.0007706473,0.009141618,0.6366794,0.0015260174],"about_ca_topic_score_codex":0.00004390257,"about_ca_topic_score_gemma":0.0000331594,"teacher_disagreement_score":0.6109524,"about_ca_system_score_codex":0.00006285554,"about_ca_system_score_gemma":0.00016446409,"threshold_uncertainty_score":0.63451123},"labels":[],"label_agreement":null},{"id":"W4407397349","doi":"10.1177/20539517241291817","title":"Artificial intelligence and personalization of insurance: Failure or delayed ignition?","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Personalization; Computer science; Computer security; Internet privacy; Business; World Wide Web","score_opus":0.12095440125521534,"score_gpt":0.2804496863328314,"score_spread":0.15949528507761607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407397349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14518523,0.00528649,0.83370906,0.0017241207,0.0010277082,0.00064866204,0.007966339,0.00006495634,0.00438741],"genre_scores_gemma":[0.9935303,0.0033468525,0.002049696,0.00038341642,0.00009731487,0.000012305619,0.00038234185,0.0000073601495,0.00019045438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990524,0.0000072011803,0.0004240852,0.00033945037,0.00003688435,0.00013995379],"domain_scores_gemma":[0.99935424,0.00003134238,0.00017303256,0.00037925082,0.000042903077,0.00001922764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038164514,0.00009351482,0.00021132386,0.00005235073,0.00012515915,0.000043314783,0.0002679728,0.00008219127,0.000044920947],"category_scores_gemma":[0.000087571345,0.00009819917,0.000052979012,0.00042545234,0.0000946533,0.0002367765,0.00018016156,0.00007959273,0.000024323988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013527727,0.00028688833,0.043257363,0.00052785676,0.00025037013,0.0000024752194,0.003026011,0.000052875774,0.00006147863,0.7513867,0.031110477,0.16990224],"study_design_scores_gemma":[0.0009908426,0.00028755964,0.2137662,0.0003614814,0.000106238134,0.000003429365,0.0075624194,0.03853428,0.00085159164,0.36384407,0.3724542,0.001237702],"about_ca_topic_score_codex":0.00016027929,"about_ca_topic_score_gemma":0.00016383144,"teacher_disagreement_score":0.84834504,"about_ca_system_score_codex":0.000029296774,"about_ca_system_score_gemma":0.000032941218,"threshold_uncertainty_score":0.4004446},"labels":[],"label_agreement":null},{"id":"W4408714232","doi":"10.1177/20539517251328250","title":"Outsourcing accountability: Extractive data practice and inequities of power in humanitarian third-party monitoring","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Global Security and Public Health","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"Patrick J. McGovern Foundation","keywords":"Accountability; Outsourcing; Power (physics); Third party; Political science; Computer security; Sociology; Public administration; Business; Political economy; Computer science; Internet privacy; Law","score_opus":0.17608894284492232,"score_gpt":0.42229314957051645,"score_spread":0.24620420672559412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408714232","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87468475,0.0070457095,0.00062049745,0.026752772,0.0028261582,0.0012000406,0.002859254,0.000161401,0.083849445],"genre_scores_gemma":[0.99646765,0.0014763366,0.001038307,0.00055591564,0.00024690627,0.000003955448,0.00013976957,0.000004832742,0.00006632383],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810106,0.00034627595,0.00033506818,0.00047416575,0.0003889054,0.00035453614],"domain_scores_gemma":[0.9976445,0.00091762375,0.000204516,0.001011754,0.00014034199,0.00008125341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060152537,0.000105148334,0.00022686538,0.00003158842,0.00047163197,0.00018401197,0.0011093563,0.00016508033,0.000016275964],"category_scores_gemma":[0.00374291,0.00010904468,0.000025645906,0.0004354241,0.00034085728,0.0024551416,0.0013723918,0.0003705642,0.0000018461781],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012633171,0.0011248072,0.20639183,0.000591672,0.0003272664,0.000008288684,0.60579485,0.0000045419188,0.0001390554,0.06633688,0.07356315,0.04559133],"study_design_scores_gemma":[0.00028505942,0.000016639022,0.04993241,0.000117267526,0.000035587072,5.043e-7,0.3423318,0.000072921874,0.000007449051,0.0012537886,0.6058114,0.0001351306],"about_ca_topic_score_codex":0.078128286,"about_ca_topic_score_gemma":0.020943945,"teacher_disagreement_score":0.5322483,"about_ca_system_score_codex":0.00018545795,"about_ca_system_score_gemma":0.00092831376,"threshold_uncertainty_score":0.9969213},"labels":[],"label_agreement":null},{"id":"W4408825570","doi":"10.1177/20539517251330182","title":"Agricultural data governance from the ground up: Exploring data justice with agri-food movements","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Agriculture, Land Use, Rural Development","field":"Agricultural and Biological Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; University of British Columbia","keywords":"Economic Justice; Corporate governance; Agriculture; Environmental justice; Political science; Sociology; Environmental resource management; Economics; Geography; Law","score_opus":0.2197085962856978,"score_gpt":0.26176085867324467,"score_spread":0.04205226238754686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408825570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96083933,0.0023044203,0.00006939326,0.004106811,0.0017457241,0.000656265,0.029581305,0.0001768811,0.00051989284],"genre_scores_gemma":[0.83292824,0.0070904274,0.0018560645,0.0044797333,0.0034136777,0.000079837155,0.14763764,0.00000625945,0.0025081122],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99680406,0.000090167676,0.00038702405,0.0014625998,0.00070675305,0.0005494033],"domain_scores_gemma":[0.9973878,0.0004276988,0.00022934537,0.0017439114,0.00009635522,0.000114854294],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00048818224,0.00038601394,0.00030174764,0.0000019496613,0.0008635328,0.00042993444,0.007891461,0.00012724604,0.00006106569],"category_scores_gemma":[0.0001310806,0.00010425701,0.000056495614,0.0007458472,0.00010815618,0.0021392195,0.008125762,0.0003659827,0.00004243386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005463044,0.00020029391,0.006530135,0.000041920466,0.00071348617,0.0000047453054,0.0006623408,0.0000030942088,0.001673059,0.00093062286,0.90936506,0.07982061],"study_design_scores_gemma":[0.0003327477,0.000035881778,0.63112366,0.000127331,0.00017947765,0.0000023287364,0.006229818,0.000085106054,0.00009304967,0.00014474947,0.36130542,0.00034040253],"about_ca_topic_score_codex":0.0021780792,"about_ca_topic_score_gemma":0.008109847,"teacher_disagreement_score":0.62459356,"about_ca_system_score_codex":0.00009064049,"about_ca_system_score_gemma":0.000052264288,"threshold_uncertainty_score":0.99989635},"labels":[],"label_agreement":null},{"id":"W4409397258","doi":"10.1177/20539517251330160","title":"Latin American critical data studies","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Politics and Society in Latin America","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Connaught Fund","keywords":"Latin Americans; Political science; Computer science; Data science; Sociology; Law","score_opus":0.3286030629847636,"score_gpt":0.4969910046229163,"score_spread":0.16838794163815268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409397258","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06769,0.030576946,0.025490759,0.45193323,0.017873123,0.0024166128,0.024515826,0.002497449,0.37700605],"genre_scores_gemma":[0.9125298,0.01699124,0.040407125,0.019693708,0.0027084723,0.000025799205,0.0012654931,0.000034142293,0.0063442183],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978438,0.00020540926,0.00027327126,0.00063135923,0.00045183455,0.00059431803],"domain_scores_gemma":[0.9960096,0.0015279509,0.00007985329,0.0020899028,0.00014930664,0.00014339911],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0014858898,0.0001456763,0.00031282357,0.000013777705,0.0011355872,0.00015664629,0.0024316853,0.00009321919,0.0000414671],"category_scores_gemma":[0.0043245205,0.00014045871,0.00009564009,0.00068020634,0.0037201322,0.00030646776,0.0025257438,0.00027866891,0.00003228988],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017442268,0.00008329516,0.002410115,0.00003692461,0.00022799635,0.0000014763043,0.01691737,3.086149e-7,0.000013042478,0.06810875,0.87094945,0.041249502],"study_design_scores_gemma":[0.00011887228,0.000012436911,0.002301879,0.0000379049,0.000085318716,7.695585e-8,0.11644918,0.0007677322,0.0000026727628,0.0035934881,0.87643874,0.0001916871],"about_ca_topic_score_codex":0.005168796,"about_ca_topic_score_gemma":0.0009074782,"teacher_disagreement_score":0.8448398,"about_ca_system_score_codex":0.00014020412,"about_ca_system_score_gemma":0.00062039355,"threshold_uncertainty_score":0.9989912},"labels":[],"label_agreement":null},{"id":"W4409722615","doi":"10.1177/20539517251334099","title":"Algorithmic accountabilities and health systems: A review and sociomaterial approach","year":2025,"lang":"en","type":"review","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sociology; Epistemology; Computer science; Data science; Engineering ethics; Engineering; Philosophy","score_opus":0.41184638221519215,"score_gpt":0.4951928313561257,"score_spread":0.08334644914093353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409722615","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.3565724e-7,0.98933846,0.000028531034,0.0029204446,0.00081936584,0.0022438746,0.0031433543,0.000089795976,0.0014159615],"genre_scores_gemma":[8.853031e-7,0.9943336,0.00048234596,0.0015441525,0.0014523404,0.00011726542,0.0013726495,0.000029709377,0.00066703226],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99639404,0.00096567575,0.00072737475,0.00082895724,0.00050651695,0.0005774596],"domain_scores_gemma":[0.99779564,0.0004648758,0.0005030935,0.00082351407,0.00015683586,0.00025603818],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.007675544,0.00040927506,0.0022858174,0.000033599357,0.0014244892,0.00086352887,0.0009794657,0.0007244877,0.000008043765],"category_scores_gemma":[0.0005437085,0.00034630863,0.00025742291,0.0003514191,0.0009695,0.00050049624,0.00097103964,0.0005683769,0.0000033316687],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.094449e-7,0.000033874676,0.0000010224334,0.29759902,0.0002870333,4.1345544e-7,0.00768517,1.7718079e-9,3.6020902e-9,0.004134604,0.16338359,0.52687496],"study_design_scores_gemma":[0.0000804505,0.000012584678,0.0000012573441,0.023994925,0.0007875538,0.000003152146,0.005649631,0.0000014921883,4.8474197e-10,0.00017332494,0.96899605,0.00029956206],"about_ca_topic_score_codex":0.010762259,"about_ca_topic_score_gemma":0.0003399391,"teacher_disagreement_score":0.8056125,"about_ca_system_score_codex":0.00037492212,"about_ca_system_score_gemma":0.0046293545,"threshold_uncertainty_score":0.9998989},"labels":[],"label_agreement":null},{"id":"W4410101507","doi":"10.1177/20539517241304678","title":"Artificial intelligence for development (AI4D): A contested notion","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Innovation and Socioeconomic Development","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université Laval","funders":"","keywords":"Development (topology); Epistemology; Sociology; Computer science; Cognitive science; Artificial intelligence; Psychology; Mathematics; Philosophy","score_opus":0.18722031574235956,"score_gpt":0.31426923470636103,"score_spread":0.12704891896400147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410101507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08094452,0.00010030529,0.8800463,0.012842705,0.0061863298,0.0017839707,0.00008576654,0.0004485476,0.017561551],"genre_scores_gemma":[0.93818456,0.000018422219,0.024490621,0.027661607,0.0017104308,0.00018926308,0.004680292,0.000030963107,0.003033843],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989279,0.0000031522222,0.0004272607,0.00033506853,0.00009835318,0.00020826822],"domain_scores_gemma":[0.999301,0.000044166,0.00013831239,0.00031281824,0.00019775209,0.000005908006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007978722,0.0001230572,0.000137342,0.00008079816,0.00033990573,0.00024691827,0.00041400126,0.00007541683,0.000047655947],"category_scores_gemma":[0.00012361346,0.00012533482,0.000051082006,0.00040627102,0.000043567943,0.00045844266,0.00035755057,0.00007543334,0.00017153275],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026652324,0.00011523578,0.00073290826,0.00020867192,0.00012001189,3.0338612e-7,0.0004610712,0.0000059892145,0.00019535786,0.18572123,0.1582459,0.65416664],"study_design_scores_gemma":[0.00015993333,0.000001527586,0.002357907,0.000041312065,0.000020166988,9.072538e-8,0.001280457,0.007997598,0.00037485617,0.0047629056,0.9827979,0.000205321],"about_ca_topic_score_codex":0.000031607848,"about_ca_topic_score_gemma":0.00007809022,"teacher_disagreement_score":0.85724,"about_ca_system_score_codex":0.0001063405,"about_ca_system_score_gemma":0.00018308249,"threshold_uncertainty_score":0.51110053},"labels":[],"label_agreement":null},{"id":"W4410177457","doi":"10.1177/20539517251319996","title":"The appification of borders: Data, migration and digitalization","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Global Security and Public Health","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The King's University; Western University; University of Ottawa; Acadia University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Data science; Sociology; Computer security; Economic geography; Political science; Geography","score_opus":0.11249039245579796,"score_gpt":0.3871943082829714,"score_spread":0.27470391582717346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410177457","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1861565,0.030884026,0.13220839,0.5017613,0.005111029,0.0045589153,0.010193557,0.0005969865,0.1285293],"genre_scores_gemma":[0.9799659,0.014779938,0.00036071558,0.0007517178,0.00018170052,0.0000045423344,0.0036294127,0.000002776816,0.00032329015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99928534,0.000097706674,0.00014143888,0.00018178472,0.00017851844,0.000115214505],"domain_scores_gemma":[0.99907565,0.000146482,0.00007284981,0.0005948544,0.00007802953,0.000032153363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014940847,0.000036184123,0.000051609895,0.000006495264,0.00057875225,0.00015913758,0.0005924041,0.00006249142,0.0000022744264],"category_scores_gemma":[0.00054840767,0.000029073031,0.000011449209,0.0003324796,0.0002281403,0.0005678281,0.00021663897,0.000043833537,0.0000011660453],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004849598,0.00005922674,0.005587803,0.000059290192,0.000033486434,2.4956998e-8,0.011175548,6.3336404e-7,0.000016544225,0.19314134,0.4937951,0.29612616],"study_design_scores_gemma":[0.00005999789,0.0000031076945,0.005071599,0.000009807538,0.000007964689,2.635078e-8,0.008341529,0.0011685474,0.0000022424294,0.0019394939,0.98336697,0.00002869918],"about_ca_topic_score_codex":0.00950681,"about_ca_topic_score_gemma":0.022786546,"teacher_disagreement_score":0.7938094,"about_ca_system_score_codex":0.000026286496,"about_ca_system_score_gemma":0.000374461,"threshold_uncertainty_score":0.99708897},"labels":[],"label_agreement":null},{"id":"W4410177675","doi":"10.1177/20539517251340603","title":"The ethics of AI value chains","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Value (mathematics); Sociology; Epistemology; Computer science; Philosophy","score_opus":0.25104686083911015,"score_gpt":0.47203002632163676,"score_spread":0.2209831654825266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410177675","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073873424,0.002620035,0.0035423068,0.8835895,0.0032966854,0.00048369772,0.0004574299,0.00012801375,0.098495],"genre_scores_gemma":[0.95062536,0.016533649,0.0006620724,0.023038037,0.00092746876,0.0000056585855,0.00006839819,0.000012838141,0.00812653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984407,0.0003468549,0.00019057555,0.00019333248,0.00053461705,0.0002939082],"domain_scores_gemma":[0.99719554,0.0016244334,0.00008405845,0.0006890395,0.00034011086,0.0000668395],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006883485,0.0000735281,0.000126152,0.000008469528,0.0022494101,0.00020248187,0.001325759,0.00035144246,0.000006371036],"category_scores_gemma":[0.004612188,0.000056006404,0.00011648403,0.00038748086,0.0012473718,0.00023287143,0.00044918648,0.00086023484,0.0000045139504],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022834695,0.00002900059,0.0003314006,0.000019892992,0.00006561705,1.6167128e-7,0.042890456,8.1154417e-7,0.000045221346,0.78420806,0.16471322,0.007693905],"study_design_scores_gemma":[0.00012262685,0.000009553606,0.0012375789,0.000039714447,0.000029085259,2.4554796e-8,0.025854034,0.00012848839,0.000044298704,0.06433446,0.9081152,0.00008493456],"about_ca_topic_score_codex":0.008350353,"about_ca_topic_score_gemma":0.008864137,"teacher_disagreement_score":0.943238,"about_ca_system_score_codex":0.00006406411,"about_ca_system_score_gemma":0.0020940495,"threshold_uncertainty_score":0.99904954},"labels":[],"label_agreement":null},{"id":"W4410311984","doi":"10.1177/20539517251338776","title":"Localized processes of platformization: The example of Surabaya","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Sharing Economy and Platforms","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Concordia University","keywords":"Computer science; Sociology","score_opus":0.11455153496901964,"score_gpt":0.2618947366047353,"score_spread":0.14734320163571563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410311984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8400327,0.0051092203,0.07004734,0.006157732,0.00319477,0.0021147493,0.00077419216,0.00044529283,0.07212399],"genre_scores_gemma":[0.99731404,0.00013958494,0.00027759603,0.0010570247,0.0002787869,0.0000071739437,0.0007222786,0.000007056605,0.00019646315],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994072,0.000001430276,0.00023247825,0.00016256918,0.0000943593,0.000101992424],"domain_scores_gemma":[0.9990483,0.00010897081,0.00018879701,0.00052889093,0.00012214489,0.0000028779375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041257188,0.000075247575,0.00014293738,0.000023868484,0.00010763309,0.00006566239,0.0006030718,0.00004721571,0.00007232875],"category_scores_gemma":[0.0001376346,0.000050725586,0.000047497,0.0005333844,0.00007954037,0.00080303685,0.0004153951,0.000056090164,0.000008560593],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001551463,0.00039669027,0.21929657,0.009327358,0.0007668257,9.471134e-7,0.0010853271,0.0002807599,0.00019779633,0.16996972,0.52038145,0.07814143],"study_design_scores_gemma":[0.0008673623,0.000004505313,0.010812313,0.00018940908,0.00012831394,4.0548164e-7,0.0010628412,0.007882987,0.0006340027,0.010172558,0.96806896,0.00017633098],"about_ca_topic_score_codex":0.0017643789,"about_ca_topic_score_gemma":0.00021663956,"teacher_disagreement_score":0.44768754,"about_ca_system_score_codex":0.0000054330203,"about_ca_system_score_gemma":0.0000728822,"threshold_uncertainty_score":0.26672247},"labels":[],"label_agreement":null},{"id":"W4413297425","doi":"10.1177/20539517251368242","title":"Gender data for good? Partnerships between tech companies and humanitarian and development organizations","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"International Development and Aid","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"High tech; Public relations; Business; Political science; Sociology","score_opus":0.3761430581028499,"score_gpt":0.38433393920093367,"score_spread":0.008190881098083747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413297425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42021945,0.008960176,0.30506128,0.124526106,0.0065956684,0.009226637,0.02307425,0.0017605647,0.100575864],"genre_scores_gemma":[0.9605625,0.00031484253,0.026925541,0.00058557815,0.00041413688,0.000014246752,0.009058356,0.000011627666,0.002113147],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991486,0.0000287825,0.00015828709,0.00033383016,0.0001554796,0.00017503706],"domain_scores_gemma":[0.9993145,0.00017199185,0.000042605163,0.00030746145,0.00011705715,0.00004640725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074180437,0.00008260368,0.00010350607,0.00002294376,0.0011095472,0.00019046084,0.00067594583,0.00006854732,0.000018210865],"category_scores_gemma":[0.00020111959,0.00008214034,0.000008003716,0.00018183756,0.0001662091,0.00032750663,0.0008811222,0.000052055962,0.0000041477183],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062210793,0.00008606433,0.17348178,0.00015442458,0.0006674754,5.3306155e-7,0.04225951,2.1462893e-7,0.000053393233,0.37819695,0.38116273,0.023930717],"study_design_scores_gemma":[0.00023223234,0.0000026565522,0.061508793,0.000019531235,0.00003441117,1.1407433e-7,0.008208194,0.000050892068,0.000021848131,0.0024334951,0.92735463,0.00013318853],"about_ca_topic_score_codex":0.0001106446,"about_ca_topic_score_gemma":0.0019512639,"teacher_disagreement_score":0.54619193,"about_ca_system_score_codex":0.000048848837,"about_ca_system_score_gemma":0.00052797864,"threshold_uncertainty_score":0.8533852},"labels":[],"label_agreement":null},{"id":"W4415283783","doi":"10.1177/20539517251386055","title":"Cosine capital: Large language models and the embedding of all things","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Koneen Säätiö","keywords":"Commodification; Abstraction; Embedding; sort; Language model; Process (computing); Modeling language; Natural language","score_opus":0.06613855722414949,"score_gpt":0.2689227084585134,"score_spread":0.2027841512343639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415283783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5763615,0.15749557,0.1999282,0.010861733,0.001032658,0.0012193454,0.010709245,0.00016794124,0.04222384],"genre_scores_gemma":[0.9960266,0.00096943486,0.00068279426,0.00069267425,0.0000557433,0.0000051049037,0.00018887703,0.000008443244,0.0013703686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991669,0.000011902282,0.00036037067,0.00027869665,0.000029930143,0.0001522069],"domain_scores_gemma":[0.998979,0.00006917912,0.00018971512,0.00072194583,0.000018671773,0.000021537588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008970158,0.0000868361,0.00034505353,0.000029860897,0.00010847578,0.00006702637,0.00038646747,0.00004832894,0.00005833407],"category_scores_gemma":[0.00004147774,0.000070607246,0.00012943351,0.00019054036,0.00008149793,0.00024809502,0.00054563343,0.00008169276,0.000007631152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021047228,0.00007122895,0.0015618289,0.00020705006,0.0009367827,8.9012343e-7,0.018646859,0.00008823376,0.000035685825,0.93293613,0.04375315,0.0017410846],"study_design_scores_gemma":[0.0022977036,0.00001299228,0.0012490404,0.00006697103,0.000104139726,0.0000018527129,0.011262544,0.755327,0.0000149547495,0.033433307,0.19596116,0.0002683262],"about_ca_topic_score_codex":0.0033594782,"about_ca_topic_score_gemma":0.00014885956,"teacher_disagreement_score":0.8995029,"about_ca_system_score_codex":0.000019057392,"about_ca_system_score_gemma":0.000010456397,"threshold_uncertainty_score":0.5078549},"labels":[],"label_agreement":null},{"id":"W4415284214","doi":"10.1177/20539517251389844","title":"China as an analytical lens for AI and society","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"China's Socioeconomic Reforms and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cognitive reframing; China; Sociotechnical system; Typology; Subject (documents); Politics; Core (optical fiber); Knowledge production","score_opus":0.07262515648705674,"score_gpt":0.3722478244106314,"score_spread":0.29962266792357467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415284214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90783995,0.001164501,0.0070720823,0.05519078,0.0015515194,0.0011175111,0.0019384264,0.00022320826,0.023902016],"genre_scores_gemma":[0.9708466,0.0055273236,0.0027609728,0.009837726,0.0013869159,0.000027461921,0.00037285974,0.000022292434,0.009217874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986975,0.000031308795,0.00020210304,0.0005262653,0.00016856543,0.00037421053],"domain_scores_gemma":[0.9991073,0.000077255216,0.00007934601,0.0005783174,0.000044435692,0.00011333377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010555144,0.0001341666,0.00022155487,0.0000063484417,0.00094745064,0.00021157967,0.0006077871,0.00019795148,0.00003192756],"category_scores_gemma":[0.00013857841,0.000117713265,0.00020549571,0.00013789066,0.000495319,0.0007717758,0.00031279723,0.00018851568,0.000007018485],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020531772,0.00016144721,0.006830062,0.00008941745,0.00025753368,5.186887e-7,0.036893062,0.0000017475884,0.0000273785,0.2098926,0.6613761,0.08444956],"study_design_scores_gemma":[0.0007425276,0.000039942497,0.056237828,0.000022907248,0.00007117136,4.992886e-7,0.007827908,0.006379842,0.0000084204075,0.01696265,0.9114542,0.0002521265],"about_ca_topic_score_codex":0.0069188853,"about_ca_topic_score_gemma":0.0017787345,"teacher_disagreement_score":0.25007802,"about_ca_system_score_codex":0.00018577505,"about_ca_system_score_gemma":0.00051667244,"threshold_uncertainty_score":0.9996941},"labels":[],"label_agreement":null},{"id":"W4417049661","doi":"10.1177/20539517251396069","title":"Cross-cultural challenges in generative AI: Addressing homophobia in diverse sociocultural contexts","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Budapesti Corvinus Egyetem","keywords":"Generative grammar; Sociocultural evolution; Context (archaeology); Viewpoints; Cultural diversity; Variety (cybernetics); Dilemma; Cultural relativism","score_opus":0.2409162857066321,"score_gpt":0.41137659182217295,"score_spread":0.17046030611554086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417049661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92385054,0.010712326,0.011639343,0.043381907,0.0050085257,0.0008482835,0.00048375127,0.00042755753,0.003647762],"genre_scores_gemma":[0.9867654,0.0012402952,0.008224338,0.0028951564,0.00020703419,0.000036681395,0.00016765103,0.000008588298,0.00045488824],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99817723,0.00012240904,0.00033430185,0.0007640149,0.00022366253,0.00037838132],"domain_scores_gemma":[0.99847627,0.00015567681,0.000096579926,0.0010330754,0.00018738175,0.000051039828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003501006,0.00020585624,0.00023985891,0.00004916647,0.00028124833,0.0005835759,0.0020420966,0.00015693252,0.0000145692975],"category_scores_gemma":[0.000085192776,0.00018103463,0.000100970945,0.000518888,0.0001837435,0.0032190417,0.0021299424,0.00051398436,0.000034603923],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059012884,0.0011770439,0.05167372,0.0004059379,0.00042362107,0.00017652693,0.21711716,0.00072624156,0.01113088,0.023440976,0.18910226,0.5045666],"study_design_scores_gemma":[0.0064867684,0.00010021738,0.61386186,0.001568933,0.000055561046,0.00004514629,0.05909009,0.17428176,0.0031742803,0.004865088,0.13440125,0.002069041],"about_ca_topic_score_codex":0.00061046553,"about_ca_topic_score_gemma":0.0046055266,"teacher_disagreement_score":0.56218815,"about_ca_system_score_codex":0.0003213783,"about_ca_system_score_gemma":0.0001564448,"threshold_uncertainty_score":0.7382378},"labels":[],"label_agreement":null},{"id":"W7082272960","doi":"10.1177/20539517251381671","title":"Data cultures: Contested meanings in a public cultural institution","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Université de Montréal","keywords":"Institution; Field (mathematics); Corporate governance; Public service; Organizational culture; Process (computing); Action (physics); Power (physics); Artifact (error)","score_opus":0.1695503626155812,"score_gpt":0.3208531667138033,"score_spread":0.1513028040982221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7082272960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04662994,0.004424156,0.6772571,0.15034677,0.004192003,0.0015825719,0.0018611184,0.0019003986,0.111805916],"genre_scores_gemma":[0.9826865,0.00017450383,0.010901685,0.002059623,0.00011733874,0.000010707442,0.0029082806,0.0000014513457,0.0011398743],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853456,0.000045511722,0.00022630718,0.00074031245,0.0001706168,0.00028266487],"domain_scores_gemma":[0.9973724,0.00005459638,0.00007500196,0.0023379934,0.000110689114,0.00004932146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006652988,0.00012998945,0.00014624414,0.000018540262,0.00019038867,0.00030684713,0.004505266,0.00011839236,0.000004873056],"category_scores_gemma":[0.0008034114,0.00010630985,0.000034924426,0.0007643847,0.00011074822,0.0015996605,0.0045024254,0.00024271937,0.000010324429],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005332569,0.00021137734,0.005211743,0.00016629654,0.00010786111,0.000018850353,0.003201649,0.000022170798,0.004635725,0.060748905,0.889603,0.03606705],"study_design_scores_gemma":[0.0005512657,0.000005875727,0.003040515,0.00008830844,0.000008166961,0.000009826666,0.0009479097,0.057080947,0.00023378422,0.001214079,0.9366296,0.00018970906],"about_ca_topic_score_codex":0.00015316794,"about_ca_topic_score_gemma":0.00021132313,"teacher_disagreement_score":0.9360566,"about_ca_system_score_codex":0.000051171824,"about_ca_system_score_gemma":0.00022170608,"threshold_uncertainty_score":0.837198},"labels":[],"label_agreement":null}]}